Aspect Term Extraction and Sentiment Classification
Drafted for v2.0 and higher versions. Note there are many breaking changes in v2.0, so you do not need to upgrade to v2.0 and higher versions if you are using code, API, checkpoints, datasets or anything from v1.0. Let’s begin the introduction.
[1]:
!pip install pyabsa -U
from pyabsa import AspectTermExtraction as ATEPC
Requirement already satisfied: pyabsa in /home/yangheng/miniconda3/lib/python3.9/site-packages (2.0.28)
Requirement already satisfied: seqeval in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (1.2.2)
Requirement already satisfied: findfile>=2.0.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (2.0.0)
Requirement already satisfied: termcolor in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (2.1.1)
Requirement already satisfied: protobuf<4.0.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (3.20.3)
Requirement already satisfied: gitpython in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (3.1.29)
Requirement already satisfied: sentencepiece in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (0.1.97)
Requirement already satisfied: typing-extensions in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (4.4.0)
Requirement already satisfied: networkx in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (3.0rc1)
Requirement already satisfied: spacy in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (3.4.3)
Requirement already satisfied: transformers>=4.18.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (4.25.1)
Requirement already satisfied: torch>=1.0.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (2.0.0.dev20221210+cu117)
Requirement already satisfied: pandas in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (1.5.2)
Requirement already satisfied: metric-visualizer>=0.8.8 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (0.8.8)
Requirement already satisfied: autocuda>=0.16 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (0.16)
Requirement already satisfied: pytorch-warmup in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (0.1.1)
Requirement already satisfied: update-checker in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (0.18.0)
Requirement already satisfied: tqdm in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (4.63.0)
Requirement already satisfied: boostaug>=2.3.5 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pyabsa) (2.3.5)
Requirement already satisfied: natsort in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (8.2.0)
Requirement already satisfied: matplotlib>=3.6.3 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (3.6.3)
Requirement already satisfied: xlsxwriter in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (3.0.7)
Requirement already satisfied: numpy in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (1.24.0rc2)
Requirement already satisfied: tikzplotlib in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (0.10.1)
Requirement already satisfied: click in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (8.1.3)
Requirement already satisfied: scipy in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (1.9.3)
Requirement already satisfied: tabulate in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (0.9.0)
Requirement already satisfied: openpyxl in /home/yangheng/miniconda3/lib/python3.9/site-packages (from metric-visualizer>=0.8.8->pyabsa) (3.0.10)
Requirement already satisfied: pyparsing>=2.2.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (3.0.9)
Requirement already satisfied: pillow>=6.2.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (9.3.0)
Requirement already satisfied: fonttools>=4.22.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (4.38.0)
Requirement already satisfied: contourpy>=1.0.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (1.0.7)
Requirement already satisfied: kiwisolver>=1.0.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (1.4.4)
Requirement already satisfied: packaging>=20.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (22.0)
Requirement already satisfied: cycler>=0.10 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (0.11.0)
Requirement already satisfied: python-dateutil>=2.7 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (2.8.2)
Requirement already satisfied: six>=1.5 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from python-dateutil>=2.7->matplotlib>=3.6.3->metric-visualizer>=0.8.8->pyabsa) (1.16.0)
Requirement already satisfied: torchtriton==2.0.0+0d7e753227 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from torch>=1.0.0->pyabsa) (2.0.0+0d7e753227)
Requirement already satisfied: sympy in /home/yangheng/miniconda3/lib/python3.9/site-packages (from torch>=1.0.0->pyabsa) (1.11.1)
Requirement already satisfied: filelock in /home/yangheng/miniconda3/lib/python3.9/site-packages (from torchtriton==2.0.0+0d7e753227->torch>=1.0.0->pyabsa) (3.8.2)
Requirement already satisfied: cmake in /home/yangheng/miniconda3/lib/python3.9/site-packages (from torchtriton==2.0.0+0d7e753227->torch>=1.0.0->pyabsa) (3.25.0)
Requirement already satisfied: pyyaml>=5.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from transformers>=4.18.0->pyabsa) (6.0)
Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from transformers>=4.18.0->pyabsa) (0.13.2)
Requirement already satisfied: requests in /home/yangheng/miniconda3/lib/python3.9/site-packages (from transformers>=4.18.0->pyabsa) (2.28.1)
Requirement already satisfied: regex!=2019.12.17 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from transformers>=4.18.0->pyabsa) (2022.10.31)
Requirement already satisfied: huggingface-hub<1.0,>=0.10.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from transformers>=4.18.0->pyabsa) (0.11.1)
Requirement already satisfied: gitdb<5,>=4.0.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from gitpython->pyabsa) (4.0.10)
Requirement already satisfied: smmap<6,>=3.0.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from gitdb<5,>=4.0.1->gitpython->pyabsa) (5.0.0)
Requirement already satisfied: et-xmlfile in /home/yangheng/miniconda3/lib/python3.9/site-packages (from openpyxl->metric-visualizer>=0.8.8->pyabsa) (1.1.0)
Requirement already satisfied: pytz>=2020.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pandas->pyabsa) (2022.6)
Requirement already satisfied: idna<4,>=2.5 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from requests->transformers>=4.18.0->pyabsa) (3.4)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from requests->transformers>=4.18.0->pyabsa) (1.26.13)
Requirement already satisfied: charset-normalizer<3,>=2 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from requests->transformers>=4.18.0->pyabsa) (2.1.1)
Requirement already satisfied: certifi>=2017.4.17 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from requests->transformers>=4.18.0->pyabsa) (2022.12.7)
Requirement already satisfied: scikit-learn>=0.21.3 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from seqeval->pyabsa) (1.2.0)
Requirement already satisfied: joblib>=1.1.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from scikit-learn>=0.21.3->seqeval->pyabsa) (1.2.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from scikit-learn>=0.21.3->seqeval->pyabsa) (3.1.0)
Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (0.10.1)
Requirement already satisfied: thinc<8.2.0,>=8.1.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (8.1.5)
Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (1.10.2)
Requirement already satisfied: typer<0.8.0,>=0.3.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (0.7.0)
Requirement already satisfied: setuptools in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (61.2.0)
Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.10 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (3.0.10)
Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (2.0.8)
Requirement already satisfied: jinja2 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (3.1.2)
Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (1.0.4)
Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (2.0.7)
Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (2.4.5)
Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (3.3.0)
Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (1.0.9)
Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (3.0.8)
Requirement already satisfied: pathy>=0.3.5 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from spacy->pyabsa) (0.10.1)
Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from pathy>=0.3.5->spacy->pyabsa) (6.2.0)
Requirement already satisfied: confection<1.0.0,>=0.0.1 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from thinc<8.2.0,>=8.1.0->spacy->pyabsa) (0.0.3)
Requirement already satisfied: blis<0.8.0,>=0.7.8 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from thinc<8.2.0,>=8.1.0->spacy->pyabsa) (0.7.9)
Requirement already satisfied: MarkupSafe>=2.0 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from jinja2->spacy->pyabsa) (2.1.1)
Requirement already satisfied: mpmath>=0.19 in /home/yangheng/miniconda3/lib/python3.9/site-packages (from sympy->torch>=1.0.0->pyabsa) (1.2.1)
Requirement already satisfied: webcolors in /home/yangheng/miniconda3/lib/python3.9/site-packages (from tikzplotlib->metric-visualizer>=0.8.8->pyabsa) (1.12)
[2023-02-14 07:40:00] (2.0.28a0) PyABSA(2.0.28a0): If you find any problems, please report them on GitHub. Thanks!
The v2.x versions are not compatible with Google Colab. Please downgrade to 1.16.27.
ATEPCModelList
There are three types of APC models for aspect term extraction, which are based on the local context focus mechanism Notice: when you select to use a model, please make sure to carefully manage the configurations, e.g., for glove-based models, you need to set hidden dim and embed_dim manually. We already provide some pre-defined configurations. Refer to the source code if you have any question e.g.,
[2]:
config = (
ATEPC.ATEPCConfigManager.get_atepc_config_english()
) # this config contains 'pretrained_bert', it is based on pretrained models
config.model = ATEPC.ATEPCModelList.FAST_LCF_ATEPC # improved version of LCF-ATEPC
[ ]:
ATEPCDatasetList
There are the datasets from publication or third-party contribution. There dataset can be downloaded and processed automatically. In pyabsa, you can pass a set of datasets to train a model. e.g., for using integrated datasets:
[4]:
from pyabsa import DatasetItem
dataset = ATEPC.ATEPCDatasetList.Restaurant14
# now the dataset is a DatasetItem object, which has a name and a list of subdatasets
# e.g., SemEval dataset contains Laptop14, Restaurant14, Restaurant16 datasets
You can use your own dataset provided that it is formatted according to ABSADatasets
[5]:
# Put your dataset into integrated_datasets folder, it this folder does not exist, you need to call:
from pyabsa import download_all_available_datasets
download_all_available_datasets()
[2023-02-14 06:08:58] (2.0.28a0) Datasets already exist in /home/yangheng/pyabsa/examples-v2/aspect_term_extraction/integrated_datasets, skip download
to pass datasets to PyABSA trainers, you can
[ ]:
my_dataset = DatasetItem("my_dataset", ["my_dataset1", "my_dataset2"])
# my_dataset1 and my_dataset2 are the dataset folders. In there folders, the train dataset is necessary
Training
Let’s prepare to train
[5]:
from pyabsa import ModelSaveOption, DeviceTypeOption
import warnings
warnings.filterwarnings("ignore")
config.batch_size = 16
config.patience = 2
config.log_step = -1
config.seed = [1]
config.verbose = False # If verbose == True, PyABSA will output the model strcture and seversal processed data examples
config.notice = (
"This is an training example for aspect term extraction" # for memos usage
)
trainer = ATEPC.ATEPCTrainer(
config=config,
dataset=dataset,
from_checkpoint="english", # if you want to resume training from our pretrained checkpoints, you can pass the checkpoint name here
auto_device=DeviceTypeOption.AUTO, # use cuda if available
checkpoint_save_mode=ModelSaveOption.SAVE_MODEL_STATE_DICT, # save state dict only instead of the whole model
load_aug=False, # there are some augmentation dataset for integrated datasets, you use them by setting load_aug=True to improve performance
)
[2023-02-14 07:40:24] (2.0.28a0) Set Model Device: cuda:1
[2023-02-14 07:40:24] (2.0.28a0) Device Name: NVIDIA GeForce RTX 3090
2023-02-14 07:40:25,512 INFO: PyABSA version: 2.0.28a0
2023-02-14 07:40:25,515 INFO: Transformers version: 4.25.1
2023-02-14 07:40:25,517 INFO: Torch version: 2.0.0.dev20221210+cu117+cuda11.7
2023-02-14 07:40:25,518 INFO: Device: NVIDIA GeForce RTX 3090
2023-02-14 07:40:25,527 INFO: Searching dataset 114.Restaurant14 in local disk
2023-02-14 07:40:25,559 INFO: You can set load_aug=True in a trainer to augment your dataset (English only yet) and improve performance.
2023-02-14 07:40:25,560 INFO: Please use a new folder to perform new text augment if the former augment in integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14 errored unexpectedly
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
convert examples to features: 14%|█▎ | 492/3608 [00:00<00:01, 1649.17it/s]
2023-02-14 07:40:27,702 WARNING: AspectTooLongWarning -> <aspect: fried mini buns with the condensed milk and the assorted fruits on beancurd> is too long, <text: The waitress remembers me and is very friendly , she knows what my regular is and that ' s the fried mini buns with the condensed milk and the assorted fruits on beancurd .>, <polarity: Positive>
convert examples to features: 47%|████▋ | 1695/3608 [00:01<00:01, 1695.67it/s]
2023-02-14 07:40:28,366 WARNING: AspectTooLongWarning -> <aspect: salad with perfectly marinated cucumbers and tomatoes with lots of shrimp and basil> is too long, <text: I ate clams oreganta and spectacular salad with perfectly marinated cucumbers and tomatoes with lots of shrimp and basil .>, <polarity: Positive>
convert examples to features: 52%|█████▏ | 1865/3608 [00:01<00:01, 1688.26it/s]
2023-02-14 07:40:28,540 WARNING: AspectTooLongWarning -> <aspect: Godmother pizza ( a sort of traditional flat pizza with an olive oil - brushed crust and less tomato sauce than usual )> is too long, <text: But they ' ve done a really nice job of offering all the typical pizzeria faves plus some terrific specials like the Godmother pizza ( a sort of traditional flat pizza with an olive oil - brushed crust and less tomato sauce than usual ) .>, <polarity: Positive>
convert examples to features: 91%|█████████ | 3278/3608 [00:02<00:00, 1550.85it/s]
2023-02-14 07:40:29,352 WARNING: AspectTooLongWarning -> <aspect: egg noodles in the beef broth with shrimp dumplings and slices of BBQ roast pork> is too long, <text: I fell in love with the egg noodles in the beef broth with shrimp dumplings and slices of BBQ roast pork .>, <polarity: Positive>
convert examples to features: 100%|██████████| 3608/3608 [00:02<00:00, 1629.85it/s]
2023-02-14 07:40:29,540 INFO: Dataset Label Details: {'Negative': 807, 'Positive': 2160, 'Neutral': 637, 'Sum': 3604}
convert examples to features: 52%|█████▏ | 581/1120 [00:00<00:00, 1878.48it/s]
2023-02-14 07:40:30,187 WARNING: AspectTooLongWarning -> <aspect: Mediterranean salads - - layered with beets , goat cheese and walnuts> is too long, <text: Generously garnished , organic grilled burgers are the most popular dish , but the Jerusalem market - style falafel wraps and Mediterranean salads - - layered with beets , goat cheese and walnuts - - are equally scrumptious .>, <polarity: Positive>
convert examples to features: 86%|████████▌ | 960/1120 [00:00<00:00, 1770.87it/s]
2023-02-14 07:40:30,513 WARNING: AspectTooLongWarning -> <aspect: Greek yogurt ( with cuccumber , dill , and garlic )> is too long, <text: Creamy appetizers - - taramasalata , eggplant salad , and Greek yogurt ( with cuccumber , dill , and garlic ) taste excellent when on warm pitas .>, <polarity: Positive>
convert examples to features: 100%|██████████| 1120/1120 [00:00<00:00, 1743.89it/s]
2023-02-14 07:40:30,514 INFO: Dataset Label Details: {'Positive': 726, 'Neutral': 196, 'Negative': 196, 'Sum': 1118}
Some weights of the model checkpoint at microsoft/deberta-v3-base were not used when initializing DebertaV2Model: ['lm_predictions.lm_head.dense.weight', 'lm_predictions.lm_head.LayerNorm.bias', 'mask_predictions.classifier.bias', 'mask_predictions.LayerNorm.bias', 'lm_predictions.lm_head.LayerNorm.weight', 'mask_predictions.dense.bias', 'mask_predictions.dense.weight', 'mask_predictions.LayerNorm.weight', 'lm_predictions.lm_head.bias', 'lm_predictions.lm_head.dense.bias', 'mask_predictions.classifier.weight']
- This IS expected if you are initializing DebertaV2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DebertaV2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
2023-02-14 07:40:32,439 INFO: Save cache dataset to fast_lcf_atepc.Restaurant14.dataset.321ddc5085105d02cabceff84699bb05c72d582117f2fcb3244b7cfd5ff9f9c0.cache
2023-02-14 07:40:33,251 INFO: cuda memory allocated:764963840
2023-02-14 07:40:33,252 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:40:33,253 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:1
2023-02-14 07:40:33,254 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:0
2023-02-14 07:40:33,255 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:40:33,255 INFO: SRD:3 --> Calling Count:9444
2023-02-14 07:40:33,256 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:40:33,257 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:40:33,257 INFO: auto_device:True --> Calling Count:2
2023-02-14 07:40:33,258 INFO: batch_size:16 --> Calling Count:4
2023-02-14 07:40:33,258 INFO: cache_dataset:True --> Calling Count:1
2023-02-14 07:40:33,258 INFO: checkpoint_save_mode:1 --> Calling Count:4
2023-02-14 07:40:33,259 INFO: cross_validate_fold:-1 --> Calling Count:0
2023-02-14 07:40:33,259 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:6
2023-02-14 07:40:33,259 INFO: dataset_name:Restaurant14 --> Calling Count:4
2023-02-14 07:40:33,259 INFO: device:cuda:1 --> Calling Count:4
2023-02-14 07:40:33,260 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:40:33,260 INFO: dropout:0.5 --> Calling Count:1
2023-02-14 07:40:33,260 INFO: dynamic_truncate:True --> Calling Count:9444
2023-02-14 07:40:33,260 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:40:33,260 INFO: evaluate_begin:0 --> Calling Count:0
2023-02-14 07:40:33,261 INFO: from_checkpoint:english --> Calling Count:0
2023-02-14 07:40:33,261 INFO: gradient_accumulation_steps:1 --> Calling Count:3
2023-02-14 07:40:33,261 INFO: hidden_dim:768 --> Calling Count:6
2023-02-14 07:40:33,261 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:40:33,262 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:2
2023-02-14 07:40:33,262 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:40:33,262 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:40:33,262 INFO: l2reg:1e-05 --> Calling Count:2
2023-02-14 07:40:33,263 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:1
2023-02-14 07:40:33,263 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:40:33,263 INFO: lcf:cdw --> Calling Count:0
2023-02-14 07:40:33,263 INFO: learning_rate:2e-05 --> Calling Count:1
2023-02-14 07:40:33,264 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:40:33,264 INFO: log_step:-1 --> Calling Count:0
2023-02-14 07:40:33,265 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:15
2023-02-14 07:40:33,265 INFO: max_seq_len:80 --> Calling Count:33056
2023-02-14 07:40:33,265 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:5
2023-02-14 07:40:33,265 INFO: model_name:fast_lcf_atepc --> Calling Count:4725
2023-02-14 07:40:33,266 INFO: model_path_to_save:checkpoints --> Calling Count:2
2023-02-14 07:40:33,266 INFO: num_epoch:10 --> Calling Count:1
2023-02-14 07:40:33,266 INFO: num_labels:6 --> Calling Count:2
2023-02-14 07:40:33,267 INFO: optimizer:adamw --> Calling Count:2
2023-02-14 07:40:33,267 INFO: output_dim:3 --> Calling Count:1
2023-02-14 07:40:33,267 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:40:33,268 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:40:33,268 INFO: patience:2 --> Calling Count:0
2023-02-14 07:40:33,268 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:5
2023-02-14 07:40:33,268 INFO: save_mode:1 --> Calling Count:0
2023-02-14 07:40:33,269 INFO: seed:1 --> Calling Count:6
2023-02-14 07:40:33,269 INFO: sep_indices:2 --> Calling Count:0
2023-02-14 07:40:33,269 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:40:33,269 INFO: spacy_model:en_core_web_sm --> Calling Count:3
2023-02-14 07:40:33,270 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:40:33,270 INFO: task_code:ATEPC --> Calling Count:1
2023-02-14 07:40:33,270 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:0
2023-02-14 07:40:33,270 INFO: use_amp:False --> Calling Count:1
2023-02-14 07:40:33,271 INFO: use_bert_spc:True --> Calling Count:0
2023-02-14 07:40:33,271 INFO: use_syntax_based_SRD:False --> Calling Count:4722
2023-02-14 07:40:33,271 INFO: verbose:False --> Calling Count:0
2023-02-14 07:40:33,271 INFO: warmup_step:-1 --> Calling Count:0
2023-02-14 07:40:33,271 INFO: window:lr --> Calling Count:0
2023-02-14 07:40:33,277 INFO: cuda memory allocated:764963840
2023-02-14 07:40:33,277 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:40:33,278 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:1
2023-02-14 07:40:33,278 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:0
2023-02-14 07:40:33,278 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:40:33,278 INFO: SRD:3 --> Calling Count:9444
2023-02-14 07:40:33,279 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:40:33,279 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:40:33,279 INFO: auto_device:True --> Calling Count:3
2023-02-14 07:40:33,279 INFO: batch_size:16 --> Calling Count:4
2023-02-14 07:40:33,280 INFO: cache_dataset:True --> Calling Count:1
2023-02-14 07:40:33,280 INFO: checkpoint_save_mode:1 --> Calling Count:4
2023-02-14 07:40:33,280 INFO: cross_validate_fold:-1 --> Calling Count:1
2023-02-14 07:40:33,280 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:6
2023-02-14 07:40:33,281 INFO: dataset_name:Restaurant14 --> Calling Count:4
2023-02-14 07:40:33,281 INFO: device:cuda:1 --> Calling Count:8
2023-02-14 07:40:33,281 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:40:33,281 INFO: dropout:0.5 --> Calling Count:1
2023-02-14 07:40:33,281 INFO: dynamic_truncate:True --> Calling Count:9444
2023-02-14 07:40:33,282 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:40:33,282 INFO: evaluate_begin:0 --> Calling Count:0
2023-02-14 07:40:33,282 INFO: from_checkpoint:english --> Calling Count:0
2023-02-14 07:40:33,282 INFO: gradient_accumulation_steps:1 --> Calling Count:3
2023-02-14 07:40:33,283 INFO: hidden_dim:768 --> Calling Count:6
2023-02-14 07:40:33,283 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:40:33,283 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:2
2023-02-14 07:40:33,283 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:40:33,283 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:40:33,284 INFO: l2reg:1e-05 --> Calling Count:2
2023-02-14 07:40:33,284 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:1
2023-02-14 07:40:33,284 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:40:33,284 INFO: lcf:cdw --> Calling Count:0
2023-02-14 07:40:33,285 INFO: learning_rate:2e-05 --> Calling Count:1
2023-02-14 07:40:33,285 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:40:33,285 INFO: log_step:-1 --> Calling Count:0
2023-02-14 07:40:33,285 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:15
2023-02-14 07:40:33,286 INFO: max_seq_len:80 --> Calling Count:33056
2023-02-14 07:40:33,286 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:5
2023-02-14 07:40:33,286 INFO: model_name:fast_lcf_atepc --> Calling Count:4725
2023-02-14 07:40:33,286 INFO: model_path_to_save:checkpoints --> Calling Count:2
2023-02-14 07:40:33,286 INFO: num_epoch:10 --> Calling Count:1
2023-02-14 07:40:33,287 INFO: num_labels:6 --> Calling Count:2
2023-02-14 07:40:33,287 INFO: optimizer:adamw --> Calling Count:2
2023-02-14 07:40:33,287 INFO: output_dim:3 --> Calling Count:1
2023-02-14 07:40:33,287 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:40:33,288 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:40:33,288 INFO: patience:2 --> Calling Count:0
2023-02-14 07:40:33,288 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:5
2023-02-14 07:40:33,288 INFO: save_mode:1 --> Calling Count:0
2023-02-14 07:40:33,289 INFO: seed:1 --> Calling Count:6
2023-02-14 07:40:33,289 INFO: sep_indices:2 --> Calling Count:0
2023-02-14 07:40:33,289 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:40:33,289 INFO: spacy_model:en_core_web_sm --> Calling Count:3
2023-02-14 07:40:33,290 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:40:33,290 INFO: task_code:ATEPC --> Calling Count:1
2023-02-14 07:40:33,290 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:0
2023-02-14 07:40:33,290 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:40:33,291 INFO: use_amp:False --> Calling Count:1
2023-02-14 07:40:33,291 INFO: use_bert_spc:True --> Calling Count:0
2023-02-14 07:40:33,291 INFO: use_syntax_based_SRD:False --> Calling Count:4722
2023-02-14 07:40:33,291 INFO: verbose:False --> Calling Count:1
2023-02-14 07:40:33,292 INFO: warmup_step:-1 --> Calling Count:0
2023-02-14 07:40:33,292 INFO: window:lr --> Calling Count:0
2023-02-14 07:40:33,302 INFO: Checkpoint downloaded at: checkpoints/ATEPC_ENGLISH_CHECKPOINT/fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43
2023-02-14 07:40:33,554 INFO: Resume trainer from Checkpoint: checkpoints/ATEPC_ENGLISH_CHECKPOINT/fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43!
2023-02-14 07:40:33,555 INFO: ***** Running training for Aspect Term Extraction and Polarity Classification *****
2023-02-14 07:40:33,556 INFO: Num examples = 3604
2023-02-14 07:40:33,557 INFO: Batch size = 16
2023-02-14 07:40:33,557 INFO: Num steps = 2250
Epoch: 0| loss_apc:0.0121 | loss_ate:0.0547 |: 100%|██████████| 226/226 [00:56<00:00, 4.00it/s, APC_ACC: 86.58(max:86.58) | APC_F1: 80.75(max:80.75) | ATE_F1: 83.24(max:83.32)]
Epoch: 1| loss_apc:0.1608 | loss_ate:0.0020 |: 100%|██████████| 226/226 [00:58<00:00, 3.87it/s, APC_ACC: 87.92(max:87.92) | APC_F1: 81.83(max:81.84) | ATE_F1: 85.36(max:85.36)]
Epoch: 2| loss_apc:0.0040 | loss_ate:0.0478 |: 100%|██████████| 226/226 [00:46<00:00, 4.90it/s, APC_ACC: 87.39(max:87.92) | APC_F1: 81.49(max:82.53) | ATE_F1: 83.32(max:85.36)]
Epoch: 3| loss_apc:0.0013 | loss_ate:0.0102 |: 100%|██████████| 226/226 [01:02<00:00, 3.62it/s, APC_ACC: 87.48(max:87.92) | APC_F1: 81.79(max:82.53) | ATE_F1: 84.09(max:85.36)]
2023-02-14 07:44:20,643 INFO:
-------------------------------------------------------------------- Metric Visualizer --------------------------------------------------------------------
╒════════════════════════════════╤═══════════════════════════════════════════════════════╤══════════╤═══════════╤══════════╤═══════╤═══════╤═══════╤═══════╕
│ Metric │ Trial │ Values │ Average │ Median │ Std │ IQR │ Min │ Max │
╞════════════════════════════════╪═══════════════════════════════════════════════════════╪══════════╪═══════════╪══════════╪═══════╪═══════╪═══════╪═══════╡
│ Max-APC-Test-Acc w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [87.92] │ 87.92 │ 87.92 │ 0 │ 0 │ 87.92 │ 87.92 │
├────────────────────────────────┼───────────────────────────────────────────────────────┼──────────┼───────────┼──────────┼───────┼───────┼───────┼───────┤
│ Max-APC-Test-F1 w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [82.53] │ 82.53 │ 82.53 │ 0 │ 0 │ 82.53 │ 82.53 │
├────────────────────────────────┼───────────────────────────────────────────────────────┼──────────┼───────────┼──────────┼───────┼───────┼───────┼───────┤
│ Max-ATE-Test-F1 w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [85.36] │ 85.36 │ 85.36 │ 0 │ 0 │ 85.36 │ 85.36 │
╘════════════════════════════════╧═══════════════════════════════════════════════════════╧══════════╧═══════════╧══════════╧═══════╧═══════╧═══════╧═══════╛
----------------------------------------------------- https://github.com/yangheng95/metric_visualizer -----------------------------------------------------
2023-02-14 07:44:20,645 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:44:20,646 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:1
2023-02-14 07:44:20,646 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:5
2023-02-14 07:44:20,647 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:44:20,647 INFO: SRD:3 --> Calling Count:9444
2023-02-14 07:44:20,648 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:44:20,648 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:44:20,649 INFO: auto_device:True --> Calling Count:907
2023-02-14 07:44:20,649 INFO: batch_size:16 --> Calling Count:6
2023-02-14 07:44:20,650 INFO: cache_dataset:True --> Calling Count:1
2023-02-14 07:44:20,650 INFO: checkpoint_save_mode:1 --> Calling Count:4
2023-02-14 07:44:20,651 INFO: cross_validate_fold:-1 --> Calling Count:2
2023-02-14 07:44:20,651 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:6
2023-02-14 07:44:20,652 INFO: dataset_name:Restaurant14 --> Calling Count:13
2023-02-14 07:44:20,652 INFO: device:cuda:1 --> Calling Count:13822
2023-02-14 07:44:20,653 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:44:20,653 INFO: dropout:0.5 --> Calling Count:1
2023-02-14 07:44:20,654 INFO: dynamic_truncate:True --> Calling Count:9444
2023-02-14 07:44:20,654 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:44:20,655 INFO: evaluate_begin:0 --> Calling Count:9
2023-02-14 07:44:20,655 INFO: from_checkpoint:english --> Calling Count:4
2023-02-14 07:44:20,655 INFO: gradient_accumulation_steps:1 --> Calling Count:3
2023-02-14 07:44:20,656 INFO: hidden_dim:768 --> Calling Count:6
2023-02-14 07:44:20,656 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:44:20,657 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:2
2023-02-14 07:44:20,657 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:44:20,658 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:44:20,658 INFO: l2reg:1e-05 --> Calling Count:2
2023-02-14 07:44:20,659 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:10
2023-02-14 07:44:20,659 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:44:20,659 INFO: lcf:cdw --> Calling Count:3073
2023-02-14 07:44:20,660 INFO: learning_rate:2e-05 --> Calling Count:1
2023-02-14 07:44:20,660 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:44:20,661 INFO: log_step:226 --> Calling Count:906
2023-02-14 07:44:20,661 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:17
2023-02-14 07:44:20,661 INFO: loss:0.05237596165388823 --> Calling Count:0
2023-02-14 07:44:20,662 INFO: max_seq_len:80 --> Calling Count:36124
2023-02-14 07:44:20,662 INFO: max_test_metrics:{'max_apc_test_acc': 87.92, 'max_apc_test_f1': 82.53, 'max_ate_test_f1': 85.36} --> Calling Count:67
2023-02-14 07:44:20,662 INFO: metrics_of_this_checkpoint:{'apc_acc': 87.48, 'apc_f1': 81.79, 'ate_f1': 84.09} --> Calling Count:24
2023-02-14 07:44:20,663 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:5
2023-02-14 07:44:20,663 INFO: model_name:fast_lcf_atepc --> Calling Count:4754
2023-02-14 07:44:20,663 INFO: model_path_to_save:checkpoints --> Calling Count:13
2023-02-14 07:44:20,664 INFO: num_epoch:10 --> Calling Count:2
2023-02-14 07:44:20,664 INFO: num_labels:6 --> Calling Count:2
2023-02-14 07:44:20,664 INFO: optimizer:adamw --> Calling Count:2
2023-02-14 07:44:20,665 INFO: output_dim:3 --> Calling Count:10
2023-02-14 07:44:20,665 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:44:20,665 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:44:20,665 INFO: patience:2 --> Calling Count:6
2023-02-14 07:44:20,666 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:8
2023-02-14 07:44:20,666 INFO: save_mode:1 --> Calling Count:10
2023-02-14 07:44:20,666 INFO: seed:1 --> Calling Count:6
2023-02-14 07:44:20,666 INFO: sep_indices:2 --> Calling Count:34540
2023-02-14 07:44:20,667 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:44:20,667 INFO: spacy_model:en_core_web_sm --> Calling Count:3
2023-02-14 07:44:20,667 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:44:20,667 INFO: task_code:ATEPC --> Calling Count:2
2023-02-14 07:44:20,668 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:1
2023-02-14 07:44:20,668 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:44:20,668 INFO: use_amp:False --> Calling Count:1809
2023-02-14 07:44:20,668 INFO: use_bert_spc:True --> Calling Count:2164
2023-02-14 07:44:20,669 INFO: use_syntax_based_SRD:False --> Calling Count:4722
2023-02-14 07:44:20,669 INFO: verbose:False --> Calling Count:1
2023-02-14 07:44:20,669 INFO: warmup_step:-1 --> Calling Count:906
2023-02-14 07:44:20,669 INFO: window:lr --> Calling Count:0
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
convert examples to features: 14%|█▍ | 509/3608 [00:00<00:01, 1704.53it/s]
2023-02-14 07:44:26,795 WARNING: AspectTooLongWarning -> <aspect: fried mini buns with the condensed milk and the assorted fruits on beancurd> is too long, <text: The waitress remembers me and is very friendly , she knows what my regular is and that ' s the fried mini buns with the condensed milk and the assorted fruits on beancurd .>, <polarity: Positive>
convert examples to features: 43%|████▎ | 1555/3608 [00:00<00:01, 1711.64it/s]
2023-02-14 07:44:27,448 WARNING: AspectTooLongWarning -> <aspect: salad with perfectly marinated cucumbers and tomatoes with lots of shrimp and basil> is too long, <text: I ate clams oreganta and spectacular salad with perfectly marinated cucumbers and tomatoes with lots of shrimp and basil .>, <polarity: Positive>
convert examples to features: 53%|█████▎ | 1907/3608 [00:01<00:01, 1698.35it/s]
2023-02-14 07:44:27,625 WARNING: AspectTooLongWarning -> <aspect: Godmother pizza ( a sort of traditional flat pizza with an olive oil - brushed crust and less tomato sauce than usual )> is too long, <text: But they ' ve done a really nice job of offering all the typical pizzeria faves plus some terrific specials like the Godmother pizza ( a sort of traditional flat pizza with an olive oil - brushed crust and less tomato sauce than usual ) .>, <polarity: Positive>
convert examples to features: 87%|████████▋ | 3148/3608 [00:01<00:00, 1738.57it/s]
2023-02-14 07:44:28,357 WARNING: AspectTooLongWarning -> <aspect: egg noodles in the beef broth with shrimp dumplings and slices of BBQ roast pork> is too long, <text: I fell in love with the egg noodles in the beef broth with shrimp dumplings and slices of BBQ roast pork .>, <polarity: Positive>
convert examples to features: 100%|██████████| 3608/3608 [00:02<00:00, 1704.25it/s]
2023-02-14 07:44:28,546 INFO: Dataset Label Details: {'Negative': 807, 'Positive': 2160, 'Neutral': 637, 'Sum': 3604}
convert examples to features: 52%|█████▏ | 581/1120 [00:00<00:00, 1919.77it/s]
2023-02-14 07:44:29,197 WARNING: AspectTooLongWarning -> <aspect: Mediterranean salads - - layered with beets , goat cheese and walnuts> is too long, <text: Generously garnished , organic grilled burgers are the most popular dish , but the Jerusalem market - style falafel wraps and Mediterranean salads - - layered with beets , goat cheese and walnuts - - are equally scrumptious .>, <polarity: Positive>
convert examples to features: 86%|████████▌ | 960/1120 [00:00<00:00, 1778.36it/s]
2023-02-14 07:44:29,523 WARNING: AspectTooLongWarning -> <aspect: Greek yogurt ( with cuccumber , dill , and garlic )> is too long, <text: Creamy appetizers - - taramasalata , eggplant salad , and Greek yogurt ( with cuccumber , dill , and garlic ) taste excellent when on warm pitas .>, <polarity: Positive>
convert examples to features: 100%|██████████| 1120/1120 [00:00<00:00, 1749.39it/s]
2023-02-14 07:44:29,525 INFO: Dataset Label Details: {'Positive': 726, 'Neutral': 196, 'Negative': 196, 'Sum': 1118}
Some weights of the model checkpoint at microsoft/deberta-v3-base were not used when initializing DebertaV2Model: ['lm_predictions.lm_head.dense.weight', 'lm_predictions.lm_head.LayerNorm.bias', 'mask_predictions.classifier.bias', 'mask_predictions.LayerNorm.bias', 'lm_predictions.lm_head.LayerNorm.weight', 'mask_predictions.dense.bias', 'mask_predictions.dense.weight', 'mask_predictions.LayerNorm.weight', 'lm_predictions.lm_head.bias', 'lm_predictions.lm_head.dense.bias', 'mask_predictions.classifier.weight']
- This IS expected if you are initializing DebertaV2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DebertaV2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
2023-02-14 07:44:31,265 INFO: Save cache dataset to fast_lcf_atepc.Restaurant14.dataset.f7dfc4d6663122b676bbcd26f3a48ff22f40b5b24d57e3afaa4038e4ab72eda4.cache
2023-02-14 07:44:31,430 INFO: cuda memory allocated:776236032
2023-02-14 07:44:31,431 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:44:31,432 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:2
2023-02-14 07:44:31,433 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:5
2023-02-14 07:44:31,433 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:44:31,434 INFO: SRD:3 --> Calling Count:18888
2023-02-14 07:44:31,435 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:44:31,436 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:44:31,437 INFO: auto_device:True --> Calling Count:908
2023-02-14 07:44:31,437 INFO: batch_size:16 --> Calling Count:10
2023-02-14 07:44:31,438 INFO: cache_dataset:True --> Calling Count:2
2023-02-14 07:44:31,438 INFO: checkpoint_save_mode:1 --> Calling Count:5
2023-02-14 07:44:31,439 INFO: cross_validate_fold:-1 --> Calling Count:2
2023-02-14 07:44:31,439 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:10
2023-02-14 07:44:31,440 INFO: dataset_name:Restaurant14 --> Calling Count:15
2023-02-14 07:44:31,440 INFO: device:cuda:1 --> Calling Count:13826
2023-02-14 07:44:31,441 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:44:31,441 INFO: dropout:0.5 --> Calling Count:2
2023-02-14 07:44:31,442 INFO: dynamic_truncate:True --> Calling Count:18888
2023-02-14 07:44:31,442 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:44:31,443 INFO: evaluate_begin:0 --> Calling Count:9
2023-02-14 07:44:31,443 INFO: from_checkpoint:english --> Calling Count:4
2023-02-14 07:44:31,444 INFO: gradient_accumulation_steps:1 --> Calling Count:6
2023-02-14 07:44:31,444 INFO: hidden_dim:768 --> Calling Count:12
2023-02-14 07:44:31,445 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:44:31,445 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:4
2023-02-14 07:44:31,446 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:44:31,446 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:44:31,446 INFO: l2reg:1e-05 --> Calling Count:4
2023-02-14 07:44:31,447 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:11
2023-02-14 07:44:31,447 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:44:31,448 INFO: lcf:cdw --> Calling Count:3073
2023-02-14 07:44:31,448 INFO: learning_rate:2e-05 --> Calling Count:2
2023-02-14 07:44:31,449 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:44:31,449 INFO: log_step:226 --> Calling Count:906
2023-02-14 07:44:31,449 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:27
2023-02-14 07:44:31,450 INFO: loss:0.05237596165388823 --> Calling Count:0
2023-02-14 07:44:31,450 INFO: max_seq_len:80 --> Calling Count:69180
2023-02-14 07:44:31,450 INFO: max_test_metrics:{'max_apc_test_acc': 87.92, 'max_apc_test_f1': 82.53, 'max_ate_test_f1': 85.36} --> Calling Count:67
2023-02-14 07:44:31,451 INFO: metrics_of_this_checkpoint:{'apc_acc': 87.48, 'apc_f1': 81.79, 'ate_f1': 84.09} --> Calling Count:24
2023-02-14 07:44:31,451 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:6
2023-02-14 07:44:31,451 INFO: model_name:fast_lcf_atepc --> Calling Count:9478
2023-02-14 07:44:31,452 INFO: model_path_to_save:checkpoints --> Calling Count:15
2023-02-14 07:44:31,452 INFO: num_epoch:10 --> Calling Count:3
2023-02-14 07:44:31,452 INFO: num_labels:6 --> Calling Count:4
2023-02-14 07:44:31,452 INFO: optimizer:adamw --> Calling Count:4
2023-02-14 07:44:31,453 INFO: output_dim:3 --> Calling Count:11
2023-02-14 07:44:31,453 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:44:31,453 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:44:31,453 INFO: patience:2 --> Calling Count:6
2023-02-14 07:44:31,454 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:11
2023-02-14 07:44:31,454 INFO: save_mode:1 --> Calling Count:11
2023-02-14 07:44:31,454 INFO: seed:2 --> Calling Count:10
2023-02-14 07:44:31,454 INFO: sep_indices:2 --> Calling Count:34540
2023-02-14 07:44:31,455 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:44:31,455 INFO: spacy_model:en_core_web_sm --> Calling Count:7
2023-02-14 07:44:31,455 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:44:31,455 INFO: task_code:ATEPC --> Calling Count:2
2023-02-14 07:44:31,455 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:1
2023-02-14 07:44:31,456 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:44:31,456 INFO: use_amp:False --> Calling Count:1810
2023-02-14 07:44:31,456 INFO: use_bert_spc:True --> Calling Count:2164
2023-02-14 07:44:31,456 INFO: use_syntax_based_SRD:False --> Calling Count:9444
2023-02-14 07:44:31,457 INFO: verbose:False --> Calling Count:1
2023-02-14 07:44:31,457 INFO: warmup_step:-1 --> Calling Count:906
2023-02-14 07:44:31,457 INFO: window:lr --> Calling Count:0
2023-02-14 07:44:31,489 INFO: cuda memory allocated:776236032
2023-02-14 07:44:31,491 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:44:31,492 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:2
2023-02-14 07:44:31,492 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:5
2023-02-14 07:44:31,493 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:44:31,493 INFO: SRD:3 --> Calling Count:18888
2023-02-14 07:44:31,494 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:44:31,494 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:44:31,495 INFO: auto_device:True --> Calling Count:909
2023-02-14 07:44:31,495 INFO: batch_size:16 --> Calling Count:10
2023-02-14 07:44:31,496 INFO: cache_dataset:True --> Calling Count:2
2023-02-14 07:44:31,496 INFO: checkpoint_save_mode:1 --> Calling Count:5
2023-02-14 07:44:31,497 INFO: cross_validate_fold:-1 --> Calling Count:3
2023-02-14 07:44:31,497 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:10
2023-02-14 07:44:31,498 INFO: dataset_name:Restaurant14 --> Calling Count:15
2023-02-14 07:44:31,498 INFO: device:cuda:1 --> Calling Count:13830
2023-02-14 07:44:31,498 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:44:31,499 INFO: dropout:0.5 --> Calling Count:2
2023-02-14 07:44:31,499 INFO: dynamic_truncate:True --> Calling Count:18888
2023-02-14 07:44:31,499 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:44:31,500 INFO: evaluate_begin:0 --> Calling Count:9
2023-02-14 07:44:31,500 INFO: from_checkpoint:english --> Calling Count:4
2023-02-14 07:44:31,501 INFO: gradient_accumulation_steps:1 --> Calling Count:6
2023-02-14 07:44:31,501 INFO: hidden_dim:768 --> Calling Count:12
2023-02-14 07:44:31,501 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:44:31,502 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:4
2023-02-14 07:44:31,502 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:44:31,502 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:44:31,503 INFO: l2reg:1e-05 --> Calling Count:4
2023-02-14 07:44:31,503 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:11
2023-02-14 07:44:31,503 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:44:31,504 INFO: lcf:cdw --> Calling Count:3073
2023-02-14 07:44:31,504 INFO: learning_rate:2e-05 --> Calling Count:2
2023-02-14 07:44:31,504 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:44:31,504 INFO: log_step:226 --> Calling Count:906
2023-02-14 07:44:31,505 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:27
2023-02-14 07:44:31,505 INFO: loss:0.05237596165388823 --> Calling Count:0
2023-02-14 07:44:31,505 INFO: max_seq_len:80 --> Calling Count:69180
2023-02-14 07:44:31,505 INFO: max_test_metrics:{'max_apc_test_acc': 87.92, 'max_apc_test_f1': 82.53, 'max_ate_test_f1': 85.36} --> Calling Count:67
2023-02-14 07:44:31,506 INFO: metrics_of_this_checkpoint:{'apc_acc': 87.48, 'apc_f1': 81.79, 'ate_f1': 84.09} --> Calling Count:24
2023-02-14 07:44:31,506 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:6
2023-02-14 07:44:31,506 INFO: model_name:fast_lcf_atepc --> Calling Count:9478
2023-02-14 07:44:31,506 INFO: model_path_to_save:checkpoints --> Calling Count:15
2023-02-14 07:44:31,507 INFO: num_epoch:10 --> Calling Count:3
2023-02-14 07:44:31,507 INFO: num_labels:6 --> Calling Count:4
2023-02-14 07:44:31,507 INFO: optimizer:adamw --> Calling Count:4
2023-02-14 07:44:31,507 INFO: output_dim:3 --> Calling Count:11
2023-02-14 07:44:31,507 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:44:31,508 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:44:31,508 INFO: patience:2 --> Calling Count:6
2023-02-14 07:44:31,508 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:11
2023-02-14 07:44:31,508 INFO: save_mode:1 --> Calling Count:11
2023-02-14 07:44:31,509 INFO: seed:2 --> Calling Count:10
2023-02-14 07:44:31,509 INFO: sep_indices:2 --> Calling Count:34540
2023-02-14 07:44:31,509 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:44:31,509 INFO: spacy_model:en_core_web_sm --> Calling Count:7
2023-02-14 07:44:31,510 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:44:31,510 INFO: task_code:ATEPC --> Calling Count:2
2023-02-14 07:44:31,510 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:1
2023-02-14 07:44:31,520 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:44:31,520 INFO: use_amp:False --> Calling Count:1810
2023-02-14 07:44:31,520 INFO: use_bert_spc:True --> Calling Count:2164
2023-02-14 07:44:31,521 INFO: use_syntax_based_SRD:False --> Calling Count:9444
2023-02-14 07:44:31,521 INFO: verbose:False --> Calling Count:2
2023-02-14 07:44:31,521 INFO: warmup_step:-1 --> Calling Count:906
2023-02-14 07:44:31,521 INFO: window:lr --> Calling Count:0
2023-02-14 07:44:31,531 INFO: Checkpoint downloaded at: checkpoints/ATEPC_ENGLISH_CHECKPOINT/fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43
2023-02-14 07:44:31,766 INFO: Resume trainer from Checkpoint: checkpoints/ATEPC_ENGLISH_CHECKPOINT/fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43!
2023-02-14 07:44:31,767 INFO: ***** Running training for Aspect Term Extraction and Polarity Classification *****
2023-02-14 07:44:31,767 INFO: Num examples = 3604
2023-02-14 07:44:31,768 INFO: Batch size = 16
2023-02-14 07:44:31,769 INFO: Num steps = 2250
Epoch: 0| loss_apc:0.0852 | loss_ate:0.0072 |: 100%|██████████| 226/226 [01:09<00:00, 3.25it/s, APC_ACC: 87.03(max:88.28) | APC_F1: 80.69(max:82.52) | ATE_F1: 84.95(max:84.95)]
Epoch: 1| loss_apc:0.0017 | loss_ate:0.0309 |: 100%|██████████| 226/226 [01:07<00:00, 3.36it/s, APC_ACC: 87.92(max:88.28) | APC_F1: 82.19(max:82.52) | ATE_F1: 85.47(max:85.75)]
Epoch: 2| loss_apc:1.7446 | loss_ate:0.0369 |: 100%|██████████| 226/226 [01:08<00:00, 3.30it/s, APC_ACC: 87.21(max:88.28) | APC_F1: 81.45(max:82.52) | ATE_F1: 85.79(max:86.06)]
Epoch: 3| loss_apc:0.0023 | loss_ate:0.0011 |: 100%|██████████| 226/226 [00:49<00:00, 4.57it/s, APC_ACC: 88.01(max:88.28) | APC_F1: 82.21(max:82.52) | ATE_F1: 85.69(max:86.06)]
2023-02-14 07:48:50,226 INFO:
----------------------------------------------------------------------- Metric Visualizer -----------------------------------------------------------------------
╒════════════════════════════════╤═══════════════════════════════════════════════════════╤════════════════╤═══════════╤══════════╤═══════╤═══════╤═══════╤═══════╕
│ Metric │ Trial │ Values │ Average │ Median │ Std │ IQR │ Min │ Max │
╞════════════════════════════════╪═══════════════════════════════════════════════════════╪════════════════╪═══════════╪══════════╪═══════╪═══════╪═══════╪═══════╡
│ Max-APC-Test-Acc w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [87.92, 88.28] │ 88.1 │ 88.1 │ 0.18 │ 0.18 │ 87.92 │ 88.28 │
├────────────────────────────────┼───────────────────────────────────────────────────────┼────────────────┼───────────┼──────────┼───────┼───────┼───────┼───────┤
│ Max-APC-Test-F1 w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [82.53, 82.52] │ 82.52 │ 82.52 │ 0.01 │ 0.01 │ 82.52 │ 82.53 │
├────────────────────────────────┼───────────────────────────────────────────────────────┼────────────────┼───────────┼──────────┼───────┼───────┼───────┼───────┤
│ Max-ATE-Test-F1 w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [85.36, 86.06] │ 85.71 │ 85.71 │ 0.35 │ 0.35 │ 85.36 │ 86.06 │
╘════════════════════════════════╧═══════════════════════════════════════════════════════╧════════════════╧═══════════╧══════════╧═══════╧═══════╧═══════╧═══════╛
-------------------------------------------------------- https://github.com/yangheng95/metric_visualizer --------------------------------------------------------
2023-02-14 07:48:50,228 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:48:50,228 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:2
2023-02-14 07:48:50,228 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:10
2023-02-14 07:48:50,228 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:48:50,228 INFO: SRD:3 --> Calling Count:18888
2023-02-14 07:48:50,229 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:48:50,229 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:48:50,229 INFO: auto_device:True --> Calling Count:1813
2023-02-14 07:48:50,229 INFO: batch_size:16 --> Calling Count:12
2023-02-14 07:48:50,229 INFO: cache_dataset:True --> Calling Count:2
2023-02-14 07:48:50,229 INFO: checkpoint_save_mode:1 --> Calling Count:5
2023-02-14 07:48:50,230 INFO: cross_validate_fold:-1 --> Calling Count:4
2023-02-14 07:48:50,230 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:10
2023-02-14 07:48:50,230 INFO: dataset_name:Restaurant14 --> Calling Count:23
2023-02-14 07:48:50,230 INFO: device:cuda:1 --> Calling Count:27643
2023-02-14 07:48:50,230 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:48:50,230 INFO: dropout:0.5 --> Calling Count:2
2023-02-14 07:48:50,231 INFO: dynamic_truncate:True --> Calling Count:18888
2023-02-14 07:48:50,231 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:48:50,231 INFO: evaluate_begin:0 --> Calling Count:18
2023-02-14 07:48:50,231 INFO: from_checkpoint:english --> Calling Count:8
2023-02-14 07:48:50,231 INFO: gradient_accumulation_steps:1 --> Calling Count:6
2023-02-14 07:48:50,232 INFO: hidden_dim:768 --> Calling Count:12
2023-02-14 07:48:50,232 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:48:50,232 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:4
2023-02-14 07:48:50,232 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:48:50,232 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:48:50,232 INFO: l2reg:1e-05 --> Calling Count:4
2023-02-14 07:48:50,233 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:20
2023-02-14 07:48:50,233 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:48:50,233 INFO: lcf:cdw --> Calling Count:6145
2023-02-14 07:48:50,233 INFO: learning_rate:2e-05 --> Calling Count:2
2023-02-14 07:48:50,234 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:48:50,234 INFO: log_step:226 --> Calling Count:1811
2023-02-14 07:48:50,234 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:29
2023-02-14 07:48:50,234 INFO: loss:0.02713842587545514 --> Calling Count:0
2023-02-14 07:48:50,235 INFO: max_seq_len:80 --> Calling Count:72248
2023-02-14 07:48:50,235 INFO: max_test_metrics:{'max_apc_test_acc': 88.28, 'max_apc_test_f1': 82.52, 'max_ate_test_f1': 86.06} --> Calling Count:134
2023-02-14 07:48:50,235 INFO: metrics_of_this_checkpoint:{'apc_acc': 88.01, 'apc_f1': 82.21, 'ate_f1': 85.69} --> Calling Count:48
2023-02-14 07:48:50,235 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:6
2023-02-14 07:48:50,235 INFO: model_name:fast_lcf_atepc --> Calling Count:9502
2023-02-14 07:48:50,235 INFO: model_path_to_save:checkpoints --> Calling Count:24
2023-02-14 07:48:50,235 INFO: num_epoch:10 --> Calling Count:4
2023-02-14 07:48:50,236 INFO: num_labels:6 --> Calling Count:4
2023-02-14 07:48:50,236 INFO: optimizer:adamw --> Calling Count:4
2023-02-14 07:48:50,236 INFO: output_dim:3 --> Calling Count:20
2023-02-14 07:48:50,236 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:48:50,236 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:48:50,236 INFO: patience:2 --> Calling Count:11
2023-02-14 07:48:50,236 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:14
2023-02-14 07:48:50,236 INFO: save_mode:1 --> Calling Count:19
2023-02-14 07:48:50,237 INFO: seed:2 --> Calling Count:10
2023-02-14 07:48:50,237 INFO: sep_indices:2 --> Calling Count:69080
2023-02-14 07:48:50,237 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:48:50,237 INFO: spacy_model:en_core_web_sm --> Calling Count:7
2023-02-14 07:48:50,237 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:48:50,237 INFO: task_code:ATEPC --> Calling Count:3
2023-02-14 07:48:50,237 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:2
2023-02-14 07:48:50,238 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:48:50,238 INFO: use_amp:False --> Calling Count:3618
2023-02-14 07:48:50,238 INFO: use_bert_spc:True --> Calling Count:4328
2023-02-14 07:48:50,238 INFO: use_syntax_based_SRD:False --> Calling Count:9444
2023-02-14 07:48:50,239 INFO: verbose:False --> Calling Count:2
2023-02-14 07:48:50,239 INFO: warmup_step:-1 --> Calling Count:1812
2023-02-14 07:48:50,239 INFO: window:lr --> Calling Count:0
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
convert examples to features: 14%|█▍ | 515/3608 [00:00<00:01, 1710.97it/s]
2023-02-14 07:48:55,565 WARNING: AspectTooLongWarning -> <aspect: fried mini buns with the condensed milk and the assorted fruits on beancurd> is too long, <text: The waitress remembers me and is very friendly , she knows what my regular is and that ' s the fried mini buns with the condensed milk and the assorted fruits on beancurd .>, <polarity: Positive>
convert examples to features: 44%|████▍ | 1582/3608 [00:00<00:01, 1731.38it/s]
2023-02-14 07:48:56,211 WARNING: AspectTooLongWarning -> <aspect: salad with perfectly marinated cucumbers and tomatoes with lots of shrimp and basil> is too long, <text: I ate clams oreganta and spectacular salad with perfectly marinated cucumbers and tomatoes with lots of shrimp and basil .>, <polarity: Positive>
convert examples to features: 54%|█████▎ | 1937/3608 [00:01<00:00, 1709.84it/s]
2023-02-14 07:48:56,384 WARNING: AspectTooLongWarning -> <aspect: Godmother pizza ( a sort of traditional flat pizza with an olive oil - brushed crust and less tomato sauce than usual )> is too long, <text: But they ' ve done a really nice job of offering all the typical pizzeria faves plus some terrific specials like the Godmother pizza ( a sort of traditional flat pizza with an olive oil - brushed crust and less tomato sauce than usual ) .>, <polarity: Positive>
convert examples to features: 89%|████████▉ | 3210/3608 [00:01<00:00, 1774.20it/s]
2023-02-14 07:48:57,093 WARNING: AspectTooLongWarning -> <aspect: egg noodles in the beef broth with shrimp dumplings and slices of BBQ roast pork> is too long, <text: I fell in love with the egg noodles in the beef broth with shrimp dumplings and slices of BBQ roast pork .>, <polarity: Positive>
convert examples to features: 100%|██████████| 3608/3608 [00:02<00:00, 1740.70it/s]
2023-02-14 07:48:57,273 INFO: Dataset Label Details: {'Negative': 807, 'Positive': 2160, 'Neutral': 637, 'Sum': 3604}
convert examples to features: 36%|███▌ | 401/1120 [00:00<00:00, 2001.31it/s]
2023-02-14 07:48:57,881 WARNING: AspectTooLongWarning -> <aspect: Mediterranean salads - - layered with beets , goat cheese and walnuts> is too long, <text: Generously garnished , organic grilled burgers are the most popular dish , but the Jerusalem market - style falafel wraps and Mediterranean salads - - layered with beets , goat cheese and walnuts - - are equally scrumptious .>, <polarity: Positive>
convert examples to features: 87%|████████▋ | 979/1120 [00:00<00:00, 1793.52it/s]
2023-02-14 07:48:58,201 WARNING: AspectTooLongWarning -> <aspect: Greek yogurt ( with cuccumber , dill , and garlic )> is too long, <text: Creamy appetizers - - taramasalata , eggplant salad , and Greek yogurt ( with cuccumber , dill , and garlic ) taste excellent when on warm pitas .>, <polarity: Positive>
convert examples to features: 100%|██████████| 1120/1120 [00:00<00:00, 1799.23it/s]
2023-02-14 07:48:58,202 INFO: Dataset Label Details: {'Positive': 726, 'Neutral': 196, 'Negative': 196, 'Sum': 1118}
Some weights of the model checkpoint at microsoft/deberta-v3-base were not used when initializing DebertaV2Model: ['lm_predictions.lm_head.dense.weight', 'lm_predictions.lm_head.LayerNorm.bias', 'mask_predictions.classifier.bias', 'mask_predictions.LayerNorm.bias', 'lm_predictions.lm_head.LayerNorm.weight', 'mask_predictions.dense.bias', 'mask_predictions.dense.weight', 'mask_predictions.LayerNorm.weight', 'lm_predictions.lm_head.bias', 'lm_predictions.lm_head.dense.bias', 'mask_predictions.classifier.weight']
- This IS expected if you are initializing DebertaV2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DebertaV2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
2023-02-14 07:48:59,887 INFO: Save cache dataset to fast_lcf_atepc.Restaurant14.dataset.70b14ee4d789e060334c3eea7126a5e56f7f9b88b04805b0c961907099a7214c.cache
2023-02-14 07:49:00,052 INFO: cuda memory allocated:776236032
2023-02-14 07:49:00,052 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:49:00,053 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:3
2023-02-14 07:49:00,053 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:10
2023-02-14 07:49:00,053 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:49:00,053 INFO: SRD:3 --> Calling Count:28332
2023-02-14 07:49:00,054 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:49:00,054 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:49:00,054 INFO: auto_device:True --> Calling Count:1814
2023-02-14 07:49:00,055 INFO: batch_size:16 --> Calling Count:16
2023-02-14 07:49:00,055 INFO: cache_dataset:True --> Calling Count:3
2023-02-14 07:49:00,055 INFO: checkpoint_save_mode:1 --> Calling Count:6
2023-02-14 07:49:00,055 INFO: cross_validate_fold:-1 --> Calling Count:4
2023-02-14 07:49:00,055 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:14
2023-02-14 07:49:00,055 INFO: dataset_name:Restaurant14 --> Calling Count:25
2023-02-14 07:49:00,055 INFO: device:cuda:1 --> Calling Count:27647
2023-02-14 07:49:00,055 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:49:00,056 INFO: dropout:0.5 --> Calling Count:3
2023-02-14 07:49:00,056 INFO: dynamic_truncate:True --> Calling Count:28332
2023-02-14 07:49:00,056 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:49:00,056 INFO: evaluate_begin:0 --> Calling Count:18
2023-02-14 07:49:00,056 INFO: from_checkpoint:english --> Calling Count:8
2023-02-14 07:49:00,056 INFO: gradient_accumulation_steps:1 --> Calling Count:9
2023-02-14 07:49:00,056 INFO: hidden_dim:768 --> Calling Count:18
2023-02-14 07:49:00,057 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:49:00,057 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:6
2023-02-14 07:49:00,057 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:49:00,057 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:49:00,057 INFO: l2reg:1e-05 --> Calling Count:6
2023-02-14 07:49:00,057 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:21
2023-02-14 07:49:00,057 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:49:00,057 INFO: lcf:cdw --> Calling Count:6145
2023-02-14 07:49:00,058 INFO: learning_rate:2e-05 --> Calling Count:3
2023-02-14 07:49:00,058 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:49:00,058 INFO: log_step:226 --> Calling Count:1811
2023-02-14 07:49:00,058 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:39
2023-02-14 07:49:00,058 INFO: loss:0.02713842587545514 --> Calling Count:0
2023-02-14 07:49:00,058 INFO: max_seq_len:80 --> Calling Count:105304
2023-02-14 07:49:00,059 INFO: max_test_metrics:{'max_apc_test_acc': 88.28, 'max_apc_test_f1': 82.52, 'max_ate_test_f1': 86.06} --> Calling Count:134
2023-02-14 07:49:00,060 INFO: metrics_of_this_checkpoint:{'apc_acc': 88.01, 'apc_f1': 82.21, 'ate_f1': 85.69} --> Calling Count:48
2023-02-14 07:49:00,060 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:7
2023-02-14 07:49:00,060 INFO: model_name:fast_lcf_atepc --> Calling Count:14226
2023-02-14 07:49:00,060 INFO: model_path_to_save:checkpoints --> Calling Count:26
2023-02-14 07:49:00,061 INFO: num_epoch:10 --> Calling Count:5
2023-02-14 07:49:00,061 INFO: num_labels:6 --> Calling Count:6
2023-02-14 07:49:00,061 INFO: optimizer:adamw --> Calling Count:6
2023-02-14 07:49:00,061 INFO: output_dim:3 --> Calling Count:21
2023-02-14 07:49:00,061 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:49:00,061 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:49:00,061 INFO: patience:2 --> Calling Count:11
2023-02-14 07:49:00,061 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:17
2023-02-14 07:49:00,062 INFO: save_mode:1 --> Calling Count:20
2023-02-14 07:49:00,062 INFO: seed:3 --> Calling Count:14
2023-02-14 07:49:00,062 INFO: sep_indices:2 --> Calling Count:69080
2023-02-14 07:49:00,062 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:49:00,062 INFO: spacy_model:en_core_web_sm --> Calling Count:11
2023-02-14 07:49:00,062 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:49:00,062 INFO: task_code:ATEPC --> Calling Count:3
2023-02-14 07:49:00,062 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:2
2023-02-14 07:49:00,063 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:49:00,063 INFO: use_amp:False --> Calling Count:3619
2023-02-14 07:49:00,063 INFO: use_bert_spc:True --> Calling Count:4328
2023-02-14 07:49:00,064 INFO: use_syntax_based_SRD:False --> Calling Count:14166
2023-02-14 07:49:00,064 INFO: verbose:False --> Calling Count:2
2023-02-14 07:49:00,064 INFO: warmup_step:-1 --> Calling Count:1812
2023-02-14 07:49:00,064 INFO: window:lr --> Calling Count:0
2023-02-14 07:49:00,094 INFO: cuda memory allocated:776236032
2023-02-14 07:49:00,095 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:49:00,095 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:3
2023-02-14 07:49:00,095 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:10
2023-02-14 07:49:00,096 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:49:00,096 INFO: SRD:3 --> Calling Count:28332
2023-02-14 07:49:00,096 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:49:00,096 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:49:00,096 INFO: auto_device:True --> Calling Count:1815
2023-02-14 07:49:00,096 INFO: batch_size:16 --> Calling Count:16
2023-02-14 07:49:00,096 INFO: cache_dataset:True --> Calling Count:3
2023-02-14 07:49:00,097 INFO: checkpoint_save_mode:1 --> Calling Count:6
2023-02-14 07:49:00,097 INFO: cross_validate_fold:-1 --> Calling Count:5
2023-02-14 07:49:00,097 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:14
2023-02-14 07:49:00,097 INFO: dataset_name:Restaurant14 --> Calling Count:25
2023-02-14 07:49:00,097 INFO: device:cuda:1 --> Calling Count:27651
2023-02-14 07:49:00,097 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:49:00,098 INFO: dropout:0.5 --> Calling Count:3
2023-02-14 07:49:00,098 INFO: dynamic_truncate:True --> Calling Count:28332
2023-02-14 07:49:00,098 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:49:00,098 INFO: evaluate_begin:0 --> Calling Count:18
2023-02-14 07:49:00,099 INFO: from_checkpoint:english --> Calling Count:8
2023-02-14 07:49:00,099 INFO: gradient_accumulation_steps:1 --> Calling Count:9
2023-02-14 07:49:00,099 INFO: hidden_dim:768 --> Calling Count:18
2023-02-14 07:49:00,099 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:49:00,099 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:6
2023-02-14 07:49:00,100 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:49:00,100 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:49:00,100 INFO: l2reg:1e-05 --> Calling Count:6
2023-02-14 07:49:00,100 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:21
2023-02-14 07:49:00,100 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:49:00,100 INFO: lcf:cdw --> Calling Count:6145
2023-02-14 07:49:00,100 INFO: learning_rate:2e-05 --> Calling Count:3
2023-02-14 07:49:00,101 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:49:00,101 INFO: log_step:226 --> Calling Count:1811
2023-02-14 07:49:00,101 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:39
2023-02-14 07:49:00,101 INFO: loss:0.02713842587545514 --> Calling Count:0
2023-02-14 07:49:00,101 INFO: max_seq_len:80 --> Calling Count:105304
2023-02-14 07:49:00,102 INFO: max_test_metrics:{'max_apc_test_acc': 88.28, 'max_apc_test_f1': 82.52, 'max_ate_test_f1': 86.06} --> Calling Count:134
2023-02-14 07:49:00,102 INFO: metrics_of_this_checkpoint:{'apc_acc': 88.01, 'apc_f1': 82.21, 'ate_f1': 85.69} --> Calling Count:48
2023-02-14 07:49:00,102 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:7
2023-02-14 07:49:00,102 INFO: model_name:fast_lcf_atepc --> Calling Count:14226
2023-02-14 07:49:00,102 INFO: model_path_to_save:checkpoints --> Calling Count:26
2023-02-14 07:49:00,102 INFO: num_epoch:10 --> Calling Count:5
2023-02-14 07:49:00,103 INFO: num_labels:6 --> Calling Count:6
2023-02-14 07:49:00,103 INFO: optimizer:adamw --> Calling Count:6
2023-02-14 07:49:00,103 INFO: output_dim:3 --> Calling Count:21
2023-02-14 07:49:00,103 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:49:00,103 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:49:00,103 INFO: patience:2 --> Calling Count:11
2023-02-14 07:49:00,103 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:17
2023-02-14 07:49:00,103 INFO: save_mode:1 --> Calling Count:20
2023-02-14 07:49:00,104 INFO: seed:3 --> Calling Count:14
2023-02-14 07:49:00,104 INFO: sep_indices:2 --> Calling Count:69080
2023-02-14 07:49:00,104 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:49:00,104 INFO: spacy_model:en_core_web_sm --> Calling Count:11
2023-02-14 07:49:00,104 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:49:00,104 INFO: task_code:ATEPC --> Calling Count:3
2023-02-14 07:49:00,105 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:2
2023-02-14 07:49:00,105 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:49:00,105 INFO: use_amp:False --> Calling Count:3619
2023-02-14 07:49:00,105 INFO: use_bert_spc:True --> Calling Count:4328
2023-02-14 07:49:00,106 INFO: use_syntax_based_SRD:False --> Calling Count:14166
2023-02-14 07:49:00,106 INFO: verbose:False --> Calling Count:3
2023-02-14 07:49:00,106 INFO: warmup_step:-1 --> Calling Count:1812
2023-02-14 07:49:00,106 INFO: window:lr --> Calling Count:0
2023-02-14 07:49:00,112 INFO: Checkpoint downloaded at: checkpoints/ATEPC_ENGLISH_CHECKPOINT/fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43
2023-02-14 07:49:00,345 INFO: Resume trainer from Checkpoint: checkpoints/ATEPC_ENGLISH_CHECKPOINT/fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43!
2023-02-14 07:49:00,345 INFO: ***** Running training for Aspect Term Extraction and Polarity Classification *****
2023-02-14 07:49:00,346 INFO: Num examples = 3604
2023-02-14 07:49:00,346 INFO: Batch size = 16
2023-02-14 07:49:00,346 INFO: Num steps = 2250
Epoch: 0| loss_apc:0.0099 | loss_ate:0.0139 |: 100%|██████████| 226/226 [01:02<00:00, 3.59it/s, APC_ACC: 85.96(max:87.21) | APC_F1: 78.04(max:81.65) | ATE_F1: 82.87(max:84.58)]
Epoch: 1| loss_apc:0.0429 | loss_ate:0.0058 |: 100%|██████████| 226/226 [01:03<00:00, 3.58it/s, APC_ACC: 88.46(max:88.46) | APC_F1: 82.98(max:82.98) | ATE_F1: 83.60(max:84.79)]
Epoch: 2| loss_apc:0.0007 | loss_ate:0.0598 |: 100%|██████████| 226/226 [01:02<00:00, 3.60it/s, APC_ACC: 87.57(max:88.46) | APC_F1: 81.32(max:82.98) | ATE_F1: 85.72(max:85.72)]
Epoch: 3| loss_apc:0.0063 | loss_ate:0.0017 |: 100%|██████████| 226/226 [01:02<00:00, 3.63it/s, APC_ACC: 88.19(max:88.46) | APC_F1: 82.75(max:82.98) | ATE_F1: 84.08(max:85.72)]
2023-02-14 07:53:15,032 INFO:
--------------------------------------------------------------------------- Metric Visualizer ---------------------------------------------------------------------------
╒════════════════════════════════╤═══════════════════════════════════════════════════════╤═══════════════════════╤═══════════╤══════════╤═══════╤═══════╤═══════╤═══════╕
│ Metric │ Trial │ Values │ Average │ Median │ Std │ IQR │ Min │ Max │
╞════════════════════════════════╪═══════════════════════════════════════════════════════╪═══════════════════════╪═══════════╪══════════╪═══════╪═══════╪═══════╪═══════╡
│ Max-APC-Test-Acc w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [87.92, 88.28, 88.46] │ 88.22 │ 88.28 │ 0.22 │ 0.27 │ 87.92 │ 88.46 │
├────────────────────────────────┼───────────────────────────────────────────────────────┼───────────────────────┼───────────┼──────────┼───────┼───────┼───────┼───────┤
│ Max-APC-Test-F1 w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [82.53, 82.52, 82.98] │ 82.68 │ 82.53 │ 0.21 │ 0.23 │ 82.52 │ 82.98 │
├────────────────────────────────┼───────────────────────────────────────────────────────┼───────────────────────┼───────────┼──────────┼───────┼───────┼───────┼───────┤
│ Max-ATE-Test-F1 w/o Valid Set │ fast_lcf_atepc-Restaurant14-microsoft/deberta-v3-base │ [85.36, 86.06, 85.72] │ 85.71 │ 85.72 │ 0.29 │ 0.35 │ 85.36 │ 86.06 │
╘════════════════════════════════╧═══════════════════════════════════════════════════════╧═══════════════════════╧═══════════╧══════════╧═══════╧═══════╧═══════╧═══════╛
------------------------------------------------------------ https://github.com/yangheng95/metric_visualizer ------------------------------------------------------------
2023-02-14 07:53:15,033 INFO: ABSADatasetsVersion:None --> Calling Count:0
2023-02-14 07:53:15,034 INFO: IOB_label_to_index:{'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5} --> Calling Count:3
2023-02-14 07:53:15,034 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x7f56f8eac2b0> --> Calling Count:15
2023-02-14 07:53:15,034 INFO: PyABSAVersion:2.0.28a0 --> Calling Count:1
2023-02-14 07:53:15,035 INFO: SRD:3 --> Calling Count:28332
2023-02-14 07:53:15,035 INFO: TorchVersion:2.0.0.dev20221210+cu117+cuda11.7 --> Calling Count:1
2023-02-14 07:53:15,035 INFO: TransformersVersion:4.25.1 --> Calling Count:1
2023-02-14 07:53:15,035 INFO: auto_device:True --> Calling Count:2719
2023-02-14 07:53:15,035 INFO: batch_size:16 --> Calling Count:18
2023-02-14 07:53:15,035 INFO: cache_dataset:True --> Calling Count:3
2023-02-14 07:53:15,036 INFO: checkpoint_save_mode:1 --> Calling Count:6
2023-02-14 07:53:15,036 INFO: cross_validate_fold:-1 --> Calling Count:6
2023-02-14 07:53:15,036 INFO: dataset_file:{'train': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Train.xml.seg.atepc'], 'test': ['integrated_datasets/atepc_datasets/110.SemEval/114.restaurant14/Restaurants_Test_Gold.xml.seg.atepc'], 'valid': []} --> Calling Count:14
2023-02-14 07:53:15,036 INFO: dataset_name:Restaurant14 --> Calling Count:33
2023-02-14 07:53:15,036 INFO: device:cuda:1 --> Calling Count:41464
2023-02-14 07:53:15,036 INFO: device_name:NVIDIA GeForce RTX 3090 --> Calling Count:1
2023-02-14 07:53:15,036 INFO: dropout:0.5 --> Calling Count:3
2023-02-14 07:53:15,037 INFO: dynamic_truncate:True --> Calling Count:28332
2023-02-14 07:53:15,037 INFO: embed_dim:768 --> Calling Count:0
2023-02-14 07:53:15,037 INFO: evaluate_begin:0 --> Calling Count:27
2023-02-14 07:53:15,038 INFO: from_checkpoint:english --> Calling Count:12
2023-02-14 07:53:15,038 INFO: gradient_accumulation_steps:1 --> Calling Count:9
2023-02-14 07:53:15,038 INFO: hidden_dim:768 --> Calling Count:18
2023-02-14 07:53:15,038 INFO: index_to_IOB_label:{1: 'B-ASP', 2: 'I-ASP', 3: 'O', 4: '[CLS]', 5: '[SEP]'} --> Calling Count:0
2023-02-14 07:53:15,038 INFO: index_to_label:{0: 'Negative', 1: 'Neutral', 2: 'Positive'} --> Calling Count:6
2023-02-14 07:53:15,038 INFO: inference_model:None --> Calling Count:0
2023-02-14 07:53:15,038 INFO: initializer:xavier_uniform_ --> Calling Count:0
2023-02-14 07:53:15,038 INFO: l2reg:1e-05 --> Calling Count:6
2023-02-14 07:53:15,039 INFO: label_list:['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]'] --> Calling Count:30
2023-02-14 07:53:15,039 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 2} --> Calling Count:0
2023-02-14 07:53:15,039 INFO: lcf:cdw --> Calling Count:9217
2023-02-14 07:53:15,039 INFO: learning_rate:2e-05 --> Calling Count:3
2023-02-14 07:53:15,039 INFO: load_aug:False --> Calling Count:1
2023-02-14 07:53:15,039 INFO: log_step:226 --> Calling Count:2716
2023-02-14 07:53:15,039 INFO: logger:<Logger fast_lcf_atepc (INFO)> --> Calling Count:41
2023-02-14 07:53:15,040 INFO: loss:0.05008033122867346 --> Calling Count:0
2023-02-14 07:53:15,040 INFO: max_seq_len:80 --> Calling Count:108372
2023-02-14 07:53:15,040 INFO: max_test_metrics:{'max_apc_test_acc': 88.46, 'max_apc_test_f1': 82.98, 'max_ate_test_f1': 85.72} --> Calling Count:200
2023-02-14 07:53:15,040 INFO: metrics_of_this_checkpoint:{'apc_acc': 88.19, 'apc_f1': 82.75, 'ate_f1': 84.08} --> Calling Count:72
2023-02-14 07:53:15,040 INFO: model:<class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'> --> Calling Count:7
2023-02-14 07:53:15,040 INFO: model_name:fast_lcf_atepc --> Calling Count:14250
2023-02-14 07:53:15,040 INFO: model_path_to_save:checkpoints --> Calling Count:35
2023-02-14 07:53:15,040 INFO: num_epoch:10 --> Calling Count:6
2023-02-14 07:53:15,041 INFO: num_labels:6 --> Calling Count:6
2023-02-14 07:53:15,041 INFO: optimizer:adamw --> Calling Count:6
2023-02-14 07:53:15,041 INFO: output_dim:3 --> Calling Count:30
2023-02-14 07:53:15,041 INFO: overwrite_cache:False --> Calling Count:0
2023-02-14 07:53:15,042 INFO: path_to_save:None --> Calling Count:1
2023-02-14 07:53:15,042 INFO: patience:2 --> Calling Count:16
2023-02-14 07:53:15,042 INFO: pretrained_bert:microsoft/deberta-v3-base --> Calling Count:20
2023-02-14 07:53:15,042 INFO: save_mode:1 --> Calling Count:28
2023-02-14 07:53:15,042 INFO: seed:3 --> Calling Count:14
2023-02-14 07:53:15,043 INFO: sep_indices:2 --> Calling Count:103620
2023-02-14 07:53:15,043 INFO: show_metric:False --> Calling Count:0
2023-02-14 07:53:15,043 INFO: spacy_model:en_core_web_sm --> Calling Count:11
2023-02-14 07:53:15,043 INFO: srd_alignment:True --> Calling Count:0
2023-02-14 07:53:15,043 INFO: task_code:ATEPC --> Calling Count:4
2023-02-14 07:53:15,043 INFO: task_name:Aspect Term Extraction and Polarity Classification --> Calling Count:3
2023-02-14 07:53:15,043 INFO: tokenizer:PreTrainedTokenizerFast(name_or_path='microsoft/deberta-v3-base', vocab_size=128000, model_max_len=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}) --> Calling Count:0
2023-02-14 07:53:15,043 INFO: use_amp:False --> Calling Count:5427
2023-02-14 07:53:15,044 INFO: use_bert_spc:True --> Calling Count:6492
2023-02-14 07:53:15,044 INFO: use_syntax_based_SRD:False --> Calling Count:14166
2023-02-14 07:53:15,044 INFO: verbose:False --> Calling Count:3
2023-02-14 07:53:15,044 INFO: warmup_step:-1 --> Calling Count:2718
2023-02-14 07:53:15,044 INFO: window:lr --> Calling Count:0
to load trained model for inference:
[16]:
aspect_extractor = trainer.load_trained_model()
assert isinstance(aspect_extractor, ATEPC.AspectExtractor)
[2023-02-14 06:46:05] (2.0.28a0) Load aspect extractor from checkpoints/fast_lcf_atepc_Restaurant14_cdw_apcacc_87.3_apcf1_81.39_atef1_86.06
[2023-02-14 06:46:05] (2.0.28a0) config: checkpoints/fast_lcf_atepc_Restaurant14_cdw_apcacc_87.3_apcf1_81.39_atef1_86.06/fast_lcf_atepc.config
[2023-02-14 06:46:05] (2.0.28a0) state_dict: checkpoints/fast_lcf_atepc_Restaurant14_cdw_apcacc_87.3_apcf1_81.39_atef1_86.06/fast_lcf_atepc.state_dict
[2023-02-14 06:46:05] (2.0.28a0) model: None
[2023-02-14 06:46:05] (2.0.28a0) tokenizer: checkpoints/fast_lcf_atepc_Restaurant14_cdw_apcacc_87.3_apcf1_81.39_atef1_86.06/fast_lcf_atepc.tokenizer
[2023-02-14 06:46:06] (2.0.28a0) Set Model Device: cuda:1
[2023-02-14 06:46:06] (2.0.28a0) Device Name: NVIDIA GeForce RTX 3090
Some weights of the model checkpoint at microsoft/deberta-v3-base were not used when initializing DebertaV2Model: ['lm_predictions.lm_head.LayerNorm.weight', 'mask_predictions.classifier.weight', 'mask_predictions.classifier.bias', 'lm_predictions.lm_head.dense.weight', 'mask_predictions.LayerNorm.bias', 'lm_predictions.lm_head.LayerNorm.bias', 'mask_predictions.LayerNorm.weight', 'mask_predictions.dense.bias', 'lm_predictions.lm_head.bias', 'mask_predictions.dense.weight', 'lm_predictions.lm_head.dense.bias']
- This IS expected if you are initializing DebertaV2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DebertaV2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Inference
Use our checkpoints to initialize a AspectExtractor and SentimentClassifier
[8]:
from pyabsa import available_checkpoints
ckpts = (
available_checkpoints()
) # This will show the available checkpoints and their detailed informantion
# find a suitable checkpoint and use the name:
aspect_extractor = ATEPC.AspectExtractor(
checkpoint="english"
) # here I use the english checkpoint which is trained on all English datasets in PyABSA
Downloading checkpoint:english ...
Notice: The pretrained model are used for testing, it is recommended to train the model on your own custom datasets
579MB [00:17, 32.61MB/s, Downloading checkpoint...]
Find zipped checkpoint: ./checkpoints\ATEPC_ENGLISH_CHECKPOINT\fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43.zip, unzipping...
Done.
If the auto-downloading failed, please download it via browser: https://huggingface.co/spaces/yangheng/PyABSA/resolve/main/checkpoints/English/ATEPC/fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43.zip
Load aspect extractor from ./checkpoints\ATEPC_ENGLISH_CHECKPOINT
config: ./checkpoints\ATEPC_ENGLISH_CHECKPOINT\fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43\fast_lcf_atepc.config
state_dict: ./checkpoints\ATEPC_ENGLISH_CHECKPOINT\fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43\fast_lcf_atepc.state_dict
model: None
tokenizer: ./checkpoints\ATEPC_ENGLISH_CHECKPOINT\fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43\fast_lcf_atepc.tokenizer
C:\Users\chuan\miniconda3\lib\subprocess.py:1052: ResourceWarning: subprocess 20756 is still running
_warn("subprocess %s is still running" % self.pid,
ResourceWarning: Enable tracemalloc to get the object allocation traceback
c:\users\chuan\onedrive - university of exeter\works\autocuda\autocuda\autocuda.py:69: ResourceWarning: unclosed file <_io.TextIOWrapper name=6 encoding='cp1252'>
results = os.popen(cmd).readlines()
ResourceWarning: Enable tracemalloc to get the object allocation traceback
C:\Users\chuan\miniconda3\lib\subprocess.py:1052: ResourceWarning: subprocess 4564 is still running
_warn("subprocess %s is still running" % self.pid,
ResourceWarning: Enable tracemalloc to get the object allocation traceback
C:\Users\chuan\miniconda3\lib\subprocess.py:1052: ResourceWarning: subprocess 25768 is still running
_warn("subprocess %s is still running" % self.pid,
ResourceWarning: Enable tracemalloc to get the object allocation traceback
C:\Users\chuan\miniconda3\lib\subprocess.py:1052: ResourceWarning: subprocess 13760 is still running
_warn("subprocess %s is still running" % self.pid,
ResourceWarning: Enable tracemalloc to get the object allocation traceback
Some weights of the model checkpoint at microsoft/deberta-v3-base were not used when initializing DebertaV2Model: ['lm_predictions.lm_head.dense.bias', 'mask_predictions.LayerNorm.weight', 'mask_predictions.classifier.weight', 'lm_predictions.lm_head.dense.weight', 'lm_predictions.lm_head.LayerNorm.bias', 'mask_predictions.dense.bias', 'mask_predictions.LayerNorm.bias', 'lm_predictions.lm_head.LayerNorm.weight', 'mask_predictions.dense.weight', 'mask_predictions.classifier.bias', 'lm_predictions.lm_head.bias']
- This IS expected if you are initializing DebertaV2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DebertaV2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
C:\Users\chuan\miniconda3\lib\site-packages\transformers\convert_slow_tokenizer.py:434: UserWarning: The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option which is not implemented in the fast tokenizers. In practice this means that the fast version of the tokenizer can produce unknown tokens whereas the sentencepiece version would have converted these unknown tokens into a sequence of byte tokens matching the original piece of text.
warnings.warn(
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Simple Prediction
[10]:
atepc_examples = [
"But the staff was so nice to us .",
"But the staff was so horrible to us .",
r"Not only was the food outstanding , but the little ` perks \' were great .",
"It took half an hour to get our check , which was perfect since we could sit , have drinks and talk !",
"It was pleasantly uncrowded , the service was delightful , the garden adorable , "
"the food -LRB- from appetizers to entrees -RRB- was delectable .",
"How pretentious and inappropriate for MJ Grill to claim that it provides power lunch and dinners !",
]
# predict interface accepts a list of example or a single example
for ex in atepc_examples:
result = aspect_extractor.predict(
text=ex,
print_result=True,
ignore_error=True, # ignore an invalid example, if it is False, invalid examples will raise Exceptions
eval_batch_size=32,
)
D:\Works\PyABSA\pyabsa\tasks\AspectTermExtraction\prediction\aspect_extractor.py:419: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
probs = [float(x) for x in F.softmax(i_apc_logits).cpu().numpy().tolist()]
The results of aspect term extraction have been saved in D:\Works\PyABSA\examples-v2\aspect_term_extraction\atepc_inference.result.json
Example 0: But the <staff:Positive Confidence:0.999491810798645> was so nice to us .
The results of aspect term extraction have been saved in D:\Works\PyABSA\examples-v2\aspect_term_extraction\atepc_inference.result.json
Example 0: But the <staff:Negative Confidence:0.9985008239746094> was so horrible to us .
The results of aspect term extraction have been saved in D:\Works\PyABSA\examples-v2\aspect_term_extraction\atepc_inference.result.json
Example 0: Not only was the <food:Positive Confidence:0.9992227554321289> outstanding , but the little ` <perks:Positive Confidence:0.9973457455635071> \ ' were great .
The results of aspect term extraction have been saved in D:\Works\PyABSA\examples-v2\aspect_term_extraction\atepc_inference.result.json
Example 0: It took half an hour to get our <check:Neutral Confidence:0.9945604205131531> , which was perfect since we could sit , have <drinks:Neutral Confidence:0.9987149238586426> and talk !
The results of aspect term extraction have been saved in D:\Works\PyABSA\examples-v2\aspect_term_extraction\atepc_inference.result.json
Example 0: It was pleasantly uncrowded , the <service:Positive Confidence:0.9989431500434875> was delightful , the <garden:Positive Confidence:0.9988502264022827> adorable , the <food:Positive Confidence:0.9944317936897278> - LRB - from <appetizers:Positive Confidence:0.9632477760314941> to <entrees:Positive Confidence:0.9780006408691406> - RRB - was delectable .
The results of aspect term extraction have been saved in D:\Works\PyABSA\examples-v2\aspect_term_extraction\atepc_inference.result.json
Example 0: How pretentious and inappropriate for MJ Grill to claim that it provides <power lunch:Neutral Confidence:0.9988718628883362> and <dinners:Neutral Confidence:0.9991008043289185> !
Batch Inference
[12]:
aspect_extractor.batch_predict(
target_file=ATEPC.ATEPCDatasetList.Restaurant16,
print_result=True,
save_result=False,
ignore_error=True,
eval_batch_size=32,
)
Try to load 116.Restaurant16 dataset from local disk
loading: integrated_datasets\apc_datasets\110.SemEval\116.restaurant16\restaurant_test.raw.inference
100%|██████████| 422/422 [00:00<00:00, 1056.77it/s, preparing apc inference dataloader...]
0%| | 0/14 [00:00<?, ?it/s, extracting aspect terms...]C:\Users\chuan\miniconda3\lib\site-packages\transformers\models\deberta_v2\modeling_deberta_v2.py:542: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
bucket_pos = np.where(abs_pos <= mid, relative_pos, log_pos * sign).astype(np.int)
100%|██████████| 14/14 [00:08<00:00, 1.70it/s, extracting aspect terms...]
100%|██████████| 710/710 [00:01<00:00, 589.13it/s, preparing apc inference dataloader...]
0%| | 0/23 [00:00<?, ?it/s, classifying aspect sentiments...]D:\Works\PyABSA\pyabsa\tasks\AspectTermExtraction\prediction\aspect_extractor.py:419: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
probs = [float(x) for x in F.softmax(i_apc_logits).cpu().numpy().tolist()]
100%|██████████| 23/23 [00:14<00:00, 1.63it/s, classifying aspect sentiments...]
Example 0: serves really good <sushi:Positive Confidence:0.9918943047523499> .
Example 1: not the biggest <portions:Negative Confidence:0.979500949382782> but adequate .
Example 2: green tea creme brulee is a must !
Example 3: – i ca n ' t say enough about <this:Positive Confidence:0.9954694509506226> place .
Example 4: it has great <sushi:Positive Confidence:0.9995418787002563> and even better <service:Positive Confidence:0.9995410442352295> .
Example 5: the entire <staff:Positive Confidence:0.9995019435882568> was extremely accomodating and tended to my every need .
Example 6: i ' ve been to this <restaurant:Positive Confidence:0.9987316727638245> over a dozen times with no complaints to date .
Example 7: the <owner:Negative Confidence:0.9984574317932129> is belligerent to guests that have a complaint .
Example 8: good <food:Positive Confidence:0.9994831085205078> !
Example 9: this is a great place to get a delicious <meal:Positive Confidence:0.9995520710945129> .
Example 10: the <staff:Positive Confidence:0.9994608759880066> is pretty friendly .
Example 11: the <onion rings:Positive Confidence:0.999536395072937> are great !
Example 12: – i was highly disappointed in <the:Negative Confidence:0.9986276626586914> food at pagoda .
Example 13: the <lemon chicken:Negative Confidence:0.6290537714958191> tasted like sticky sweet donuts and the <honey walnut prawns:Neutral Confidence:0.5503287315368652> , the few they actually give you . . . . . were not good .
Example 14: nice <ambience:Positive Confidence:0.9995552897453308> , but highly overrated <place:Negative Confidence:0.9987647533416748> .
Example 15: worst <service:Negative Confidence:0.9989626407623291> i ever had
Example 16: everyone that sat in the back outside agreed that it was the worst <service:Negative Confidence:0.9992260932922363> we had ever received .
Example 17: our <waiter:Negative Confidence:0.9992457628250122> was non - existent and after our <food:Neutral Confidence:0.9972600936889648> finally arrived over an hour after we ordered , we were not given any water or utensils .
Example 18: i complained to the <manager:Negative Confidence:0.9988617897033691> , but he was not even apologetic .
Example 19: fabulous italian <food:Positive Confidence:0.9995290040969849> !
Example 20: – i highly recommend mioposto .
Example 21: i am so happy to have a wonderful italian <restaurant:Positive Confidence:0.999534010887146> in my neighborhood .
Example 22: the <wine list:Positive Confidence:0.9995235204696655> is wonderful and the <food:Positive Confidence:0.9993736147880554> reminds me of my recent trip to italy .
Example 23: i love this restaurant
Example 24: – i will never forget the <amazing:Positive Confidence:0.999476969242096> meal <,:Positive Confidence:0.9994877576828003> service , <and:Positive Confidence:0.999508261680603> ambiance i experience at this restaurant .
Example 25: the <wine list:Positive Confidence:0.9993898868560791> is incredible and extensive and diverse , the <food:Positive Confidence:0.9991851449012756> is all incredible and the <staff:Positive Confidence:0.9992597699165344> was all very nice , good at their jobs and cultured .
Example 26: i have not a bad thing to say about this <place:Positive Confidence:0.9994818568229675> .
Example 27: the <food:Positive Confidence:0.9995119571685791> was great !
Example 28: it ' s * very * reasonably <priced:Positive Confidence:0.9991320967674255> , esp for the quality of the <food:Positive Confidence:0.6916458010673523> .
Example 29: i had the kafta plate and it was perfect .
Example 30: finally a <meal:Positive Confidence:0.9992990493774414> that you will remember for a long time !
Example 31: – in a age of incremental cost cutting in restaurants , its nice to see a place that bucks that trend , and just plain delivers high <quality:Positive Confidence:0.9995212554931641> food and <good:Positive Confidence:0.9995354413986206> service , period .
Example 32: this is the place to relax and enjoy the finest quality <food:Positive Confidence:0.9995115995407104> the industry can offer .
Example 33: caution - its real <food:Neutral Confidence:0.6337648034095764> for people who love the best .
Example 34: i liked the <atmosphere:Positive Confidence:0.9994756579399109> very much but the <food:Negative Confidence:0.6525688171386719> was not worth the price .
Example 35: i may not be a <sushi:Neutral Confidence:0.8712786436080933> guru but i can tell you that the <food:Neutral Confidence:0.9292333126068115> here is just okay and that there is not much else to it .
Example 36: rice is too dry , <tuna:Negative Confidence:0.9943233728408813> was n ' t so fresh either .
Example 37: i have eaten here three times and have found the <quality:Positive Confidence:0.9959967136383057> and <variety:Positive Confidence:0.992890477180481> of the <fish:Positive Confidence:0.8828207850456238> to be excellent .
Example 38: however , the <value:Negative Confidence:0.9926034808158875> and <service:Negative Confidence:0.9974547028541565> are both severely lacking .
Example 39: furthermore , while the <fish:Positive Confidence:0.999484658241272> is unquestionably fresh , <rolls:Negative Confidence:0.9989215135574341> tend to be inexplicably bland .
Example 40: the <service:Negative Confidence:0.9895910620689392> ranges from mediocre to offensive .
Example 41: on a recent trip , our <waiter:Negative Confidence:0.9311105012893677> was extremely dismissive , while no less than three <staff members:Negative Confidence:0.999186098575592> waited hand - and - foot on a pair of japanese girls seated nearby .
Example 42: freshest <sushi:Positive Confidence:0.9995357990264893> – i love this restaurant .
Example 43: freshest <sushi:Positive Confidence:0.9995357990264893> – i love this restaurant .
Example 44: they pay such detail to everything from <miso soup:Positive Confidence:0.9039835929870605> to complex <rolls:Positive Confidence:0.9240456223487854> .
Example 45: the <sashimi:Positive Confidence:0.9995050430297852> was the freshest and most tender i have ever tasted .
Example 46: their <apps:Positive Confidence:0.9992740750312805> are all delicious .
Example 47: the only drawback is that this <place:Negative Confidence:0.9942002296447754> is really expensive and the <portions:Negative Confidence:0.9976645708084106> are on the small side .
Example 48: but the <space:Positive Confidence:0.9738205671310425> is small and lovely , and the <service:Positive Confidence:0.9992954730987549> is helpful .
Example 49: – <the:Neutral Confidence:0.7998533844947815> food was not great & <the:Neutral Confidence:0.7998533844947815> waiters were rude .
Example 50: great service
Example 51: my <service:Positive Confidence:0.9993281364440918> was stellar !
Example 52: the bus boy even spotted that my <table:Negative Confidence:0.9665725827217102> was shaking a stabilized it for me .
Example 53: food was fine , with a some little - tastier - than - normal salsa .
Example 54: the <food:Positive Confidence:0.980989396572113> was great , the <margaritas:Neutral Confidence:0.8368481993675232> too but the <waitress:Negative Confidence:0.9979914426803589> was too busy being nice to her other larger party than to take better care of my friend and me .
Example 55: mama mia – i live in the neighborhood and feel lucky to live by such a great <pizza place:Positive Confidence:0.9995602965354919> .
Example 56: the only problem is you really have to warm up the <pizza:Negative Confidence:0.9986129999160767> before it ' s edible , even when you order ahead .
Example 57: best <sushi:Positive Confidence:0.9995018243789673> in town .
Example 58: the best <calamari:Positive Confidence:0.9995052814483643> in seattle !
Example 59: – . . . and the <best summertime:Positive Confidence:0.9994235038757324> deck experience - - they will even bring you a blanket if you get cold in the seattle evening weather .
Example 60: a perfect <place:Positive Confidence:0.9993807077407837> to take out of town guests any time of the year .
Example 61: endless fun , awesome <music:Positive Confidence:0.9994920492172241> , great <staff:Positive Confidence:0.9994169473648071> ! ! !
Example 62: – by far the <best:Positive Confidence:0.999479353427887> bar in the east village . . .
Example 63: every time " 0 - sixtynine " is called the <bartender:Neutral Confidence:0.9255101084709167> buys everyone <drinks:Neutral Confidence:0.9983686804771423> !
Example 64: great draft and bottle selection and the <pizza:Positive Confidence:0.9991810917854309> rocks .
Example 65: definitely has one of the best <jukebox:Positive Confidence:0.9989033937454224> ' s i ' ve seen in a long long <time:Neutral Confidence:0.9596619009971619> .
Example 66: the <food:Positive Confidence:0.9993151426315308> is great , the <bartenders:Positive Confidence:0.9899492263793945> go that extra mile .
Example 67: the <owners:Positive Confidence:0.9993649125099182> are great fun and the <beer selection:Positive Confidence:0.9994671940803528> is worth staying for .
Example 68: and the <upstairs:Positive Confidence:0.9982813596725464> is a great place to hang out .
Example 69: not alot of smoking places left in new york , but i have found my favorite smoking balconey in the city .
Example 70: the <sushi:Positive Confidence:0.9992817044258118> here is delicious !
Example 71: they have a wide <variety of fish:Positive Confidence:0.99951171875> and they even list which oceans they come from ; atlantic or pacific .
Example 72: i ' ve had the <jellyfish:Neutral Confidence:0.6333025693893433> , <horse mackerel:Positive Confidence:0.5348017811775208> , <blue fin tuna:Positive Confidence:0.818905234336853> and the <sake ikura roll:Positive Confidence:0.9987422823905945> among others , and they were all good .
Example 73: my only negative comment is that i wish the pieces were a little bigger .
Example 74: the <decor:Positive Confidence:0.7067055702209473> is rustic , traditional <japanese:Positive Confidence:0.998703122138977> .
Example 75: the <crowd:Negative Confidence:0.8289292454719543> is mixed yuppies , young and old .
Example 76: the <service:Positive Confidence:0.9995338916778564> was courteous and attentive .
Example 77: mediocre food
Example 78: the <outside patio area:Neutral Confidence:0.998214602470398> has an abbreviated <menu:Negative Confidence:0.692884087562561> .
Example 79: my g / f and i both agreed the <food:Negative Confidence:0.9981821775436401> was very mediocre especially considering the <price:Neutral Confidence:0.9906663298606873> .
Example 80: we are locals , and get the feeling the only way this place survives with such average <food:Neutral Confidence:0.5666136741638184> is because most customers are probably one - time customer tourists .
Example 81: service was decent .
Example 82: drinks were good .
Example 83: unless you are just stopping in for a few <drinks:Negative Confidence:0.8302331566810608> i would n ' t recommend going here .
Example 84: excellent <food:Positive Confidence:0.998980700969696> , nice <ambience:Positive Confidence:0.9993098974227905> , fairly expensive
Example 85: – i loved <the pumpkin:Positive Confidence:0.9938144683837891> ravioli and <the goat cheese:Positive Confidence:0.9954850673675537> gnocchi ( 5 big ones to <a:Positive Confidence:0.9944508075714111> plate instead of 20 or so little gnocchis ) and my sister loved <her filet:Positive Confidence:0.998202919960022> mignon <on top of:Positive Confidence:0.5841072797775269> spinach <and mashed:Neutral Confidence:0.9937542080879211> potatoes .
Example 86: the <ambiance:Positive Confidence:0.9986409544944763> was a peaceful and relaxing break amongst all the kids running around in downtown <disney:Neutral Confidence:0.9993114471435547> .
Example 87: it was romantic - and even nice even with my sister , reminded me of italy , and had <artwork:Positive Confidence:0.9994039535522461> and <music:Positive Confidence:0.9993734955787659> that kept up the feeling of being in a mediterrean villa .
Example 88: best <indian food:Positive Confidence:0.9994983673095703> in l . a .
Example 89: the chicken curry and <chicken tikka masala:Positive Confidence:0.999313235282898> are my favorite <meat dishes:Positive Confidence:0.9994175434112549> .
Example 90: the chana masala ( garbanzo beans ) are also excellent .
Example 91: it ' s located in a strip mall near the beverly center , not the greatest <location:Positive Confidence:0.7627604007720947> , but the <food:Positive Confidence:0.9994645714759827> keeps me coming back for more .
Example 92: never too crowded and always great <service:Positive Confidence:0.9995104074478149> .
Example 93: i think i have probably tried each item on their <menu:Positive Confidence:0.8619088530540466> at least once it is all excellent .
Example 94: i can highly recommend their various saag and <paneer:Positive Confidence:0.9994128942489624> and <korma:Positive Confidence:0.9995129108428955> .
Example 95: i appreciate their <delivery:Positive Confidence:0.9995219707489014> too .
Example 96: nice <food:Negative Confidence:0.7750080227851868> but no <spice:Negative Confidence:0.9987373948097229> !
Example 97: – i really enjoyed <my:Positive Confidence:0.9995012283325195> meal here .
Example 98: i had yummy <lamb korma:Positive Confidence:0.999265730381012> , <saag paneer:Positive Confidence:0.9913451671600342> , samosas , <naan:Positive Confidence:0.9990869760513306> , etc .
Example 99: the <food:Positive Confidence:0.7221636772155762> was all good but it was way too mild .
Example 100: i should have thought to bring it up but never expected the <food:Positive Confidence:0.9988858103752136> to be that mild .
Example 101: the <naan:Positive Confidence:0.9993488192558289> was some of the best i ' ve had and i really enjoyed the <bhartha:Positive Confidence:0.9990021586418152> , not too tomatoey .
Example 102: even the <chickpeas:Positive Confidence:0.902833878993988> , which i normally find too dry , were good .
Example 103: – i do n ' t understand how i was a stranger to this place for so long . . . <the fajita:Positive Confidence:0.9990170001983643> salad , <the:Positive Confidence:0.9941266775131226> colorado , the fajitas - everything is delicious .
Example 104: i love the warm & cosy <environment:Positive Confidence:0.9994667172431946> .
Example 105: i just found out that you can have the <place:Positive Confidence:0.9993785619735718> to yourself on nights and weekends for a private party - ca n ' t wait to celebrate my next birthday there .
Example 106: best restaurant in the world , great <decor:Positive Confidence:0.999530553817749> , great customer <service:Positive Confidence:0.9995130300521851> , friendly manager
Example 107: i am never disappointed with there <food:Positive Confidence:0.9994838237762451> .
Example 108: the <atmosphere:Positive Confidence:0.9994964599609375> is great .
Example 109: great lunch spot
Example 110: – great financial district <mexican:Positive Confidence:0.9994434714317322> spot .
Example 111: always busy , but they are good at <seating:Positive Confidence:0.9991809725761414> you promptly and have quick <service:Positive Confidence:0.999535083770752> .
Example 112: everything i ' ve had here is good , <taco salads:Positive Confidence:0.999190628528595> , <burritos:Positive Confidence:0.9990296363830566> , <enchiladas:Positive Confidence:0.9992152452468872> i love this place .
Example 113: also have great <margaritas:Positive Confidence:0.999396800994873> !
Example 114: lebanese <food:Positive Confidence:0.9990516304969788> ! yum !
Example 115: – i ' ve been <to open:Neutral Confidence:0.5608765482902527> sesame only once , but i ' m still reeling from the experience ! !
Example 116: the <food:Positive Confidence:0.9995285272598267> is simply unforgettable !
Example 117: the presentation of the <food:Positive Confidence:0.9964504241943359> was an added bonus , it <looked:Positive Confidence:0.99901282787323> just as great as it tasted !
Example 118: my best friend had the <chicken shawarma:Positive Confidence:0.9969291090965271> and she still raves about it being the best anywhere !
Example 119: the <staff:Positive Confidence:0.999352753162384> are friendly and the <decor:Positive Confidence:0.9994439482688904> was ethic and colorful .
Example 120: go to open <sesame:Positive Confidence:0.8671886324882507> ! ! !
Example 121: holy <hummus:Positive Confidence:0.9993064403533936> !
Example 122: – <the:Positive Confidence:0.9981503486633301> food is here is incredible , though <the:Positive Confidence:0.9981503486633301> quality is inconsistent <during:Neutral Confidence:0.9781894087791443> lunch .
Example 123: dinners have always been excellent , in terms of <food quality:Positive Confidence:0.9995406866073608> .
Example 124: the <open sesame combo plate:Neutral Confidence:0.9086601734161377> is a bargain for the heap of <food:Positive Confidence:0.9993484616279602> given .
Example 125: the side <of potatoes:Positive Confidence:0.9984580278396606> is to die for , as is the <labne ( yogurt dip:Neutral Confidence:0.9975995421409607> ) .
Example 126: also , they serve the best <hummus:Positive Confidence:0.9969450831413269> in america , with a drizzle of fragrant <olive oil:Neutral Confidence:0.9849721789360046> ( which , i believe is the traditional way ) !
Example 127: the only drawback is the crowded <seating:Negative Confidence:0.9983285069465637> and the slow <service:Negative Confidence:0.9989609718322754> .
Example 128: however , this <place:Positive Confidence:0.9994357228279114> is a gem , and i wo n ' t stop going back .
Example 129: great beer
Example 130: – my first time <to:Negative Confidence:0.9985804557800293> dine at this restaurant was with my son and it was absolutely horrible !
Example 131: i swore never to return for a warm <beer:Neutral Confidence:0.8072358965873718> and mediocre <meal:Negative Confidence:0.9987406134605408> .
Example 132: the <band:Positive Confidence:0.9994733929634094> was very good and the <service:Positive Confidence:0.9994875192642212> was attentive .
Example 133: we ordered a selection of the small <plates:Neutral Confidence:0.996452808380127> , and the shoe string onions , <goat cheese pizza:Positive Confidence:0.9280349612236023> , <grilled asparagus:Positive Confidence:0.9886205792427063> and fried <brie:Positive Confidence:0.926285982131958> with fruit were all very good .
Example 134: we have since returned and also had a great experience , sampling more small <plates:Neutral Confidence:0.9978274703025818> and a variety of the <beer:Positive Confidence:0.9994603991508484> ( cold and good ) .
Example 135: we did have the same <waiter:Negative Confidence:0.5510749220848083> the second time , so maybe the <service:Neutral Confidence:0.6340768337249756> is spotty and our luck is good .
Example 136: sunday afternoons there is a <band:Positive Confidence:0.9977512955665588> playing and it is lots of fun .
Example 137: seattle ' s best winelist
Example 138: – ray ' s ( suprisingly ) has the city ' s best & most <diverse wine:Positive Confidence:0.9995744824409485> list .
Example 139: the <sommelier:Positive Confidence:0.9994843006134033> is fantastic , down - to - earth , & extremely knowlegable .
Example 140: i would go back for the <wine:Positive Confidence:0.9994658827781677> experience alone .
Example 141: not the <place:Negative Confidence:0.998117208480835> it once was
Example 142: – it is sad to see <a:Negative Confidence:0.9824364185333252> place that was once " the " place to meet and eat <for:Neutral Confidence:0.9982988238334656> bfast <or:Neutral Confidence:0.9985659718513489> lunch , now be the place that is a big " dont bother . "
Example 143: the <food:Negative Confidence:0.9592967629432678> is not what it once was ( potions have seriously seen downsizing ) <prices:Negative Confidence:0.9954214692115784> have gone up , and the <service:Negative Confidence:0.9962913990020752> is the worst i have experienced anywhere ( including mainland europe ) .
Example 144: what may be interesting to most is the worst sevice / <attitude:Negative Confidence:0.9961094260215759> comes from the <owners:Negative Confidence:0.996134877204895> of this establishment .
Example 145: this establishment really made a marked decline after ( and this is recurring story ) the airing of food televisions " <diners:Neutral Confidence:0.9358963370323181> , drive - ins , and dives " hosted by <guy fieri:Negative Confidence:0.9963035583496094> , in which schooner or later was subject of .
Example 146: perhaps now , scooner or later falls into the " dive " category .
Example 147: i hope one day scooner or later returns to what it once was .
Example 148: open & cool <place:Positive Confidence:0.999516487121582> with the best <pizza:Positive Confidence:0.9994869232177734> and coffee
Example 149: – mioposto has a very creative & <delicious pizza:Positive Confidence:0.999563992023468> menu .
Example 150: the <coffe:Positive Confidence:0.9991612434387207> is very good , too .
Example 151: great open and friendly <ambience:Positive Confidence:0.9995090961456299> .
Example 152: this <place:Positive Confidence:0.9995471835136414> is charming and relaxing .
Example 153: the <servers:Positive Confidence:0.9990178346633911> behind the <counter:Neutral Confidence:0.9716606736183167> are always friendly and helpful .
Example 154: it ' s a great <place:Positive Confidence:0.9990954399108887> to enjoy <food:Positive Confidence:0.9993359446525574> and meet friends .
Example 155: – after 12 years in seattle ray ' <s:Positive Confidence:0.8511929512023926> rates as the place we always go back to .
Example 156: great <food:Positive Confidence:0.9994603991508484> , spectacular <location:Positive Confidence:0.9995120763778687> , and friendly <service:Positive Confidence:0.9995414018630981> keep us coming back year after year .
Example 157: enjoyed the food
Example 158: food was good and cheap .
Example 159: i had the <kafta:Positive Confidence:0.9992228746414185> plate and i enjoyed it .
Example 160: atmosphere was nice .
Example 161: service was kind of slow , our <waitress:Negative Confidence:0.998261034488678> took forever to give us our check even though it was n ' t that busy .
Example 162: still i would recommend this <place:Positive Confidence:0.999100923538208> .
Example 163: what else can you say nice people amazing <food:Positive Confidence:0.9994025230407715> wow
Example 164: great <food:Positive Confidence:0.9995244741439819> with an awesome <atmosphere:Positive Confidence:0.9995433688163757> !
Example 165: <–:Neutral Confidence:0.977412760257721> eggs <,:Neutral Confidence:0.9747578501701355> pancakes <,:Neutral Confidence:0.9747578501701355> potatoes , <fresh:Neutral Confidence:0.8132956624031067> fruit <and:Positive Confidence:0.8652808666229248> yogurt - - everything they serve is delicious .
Example 166: the best <place:Positive Confidence:0.9992796778678894> for a leisure sunday <breakfast:Neutral Confidence:0.6227761507034302> amidst yachts , then take a stroll through the nearby farmer ' s market .
Example 167: great <meal:Positive Confidence:0.9981635212898254> – the <fish:Positive Confidence:0.9971831440925598> on the <omikase platter:Positive Confidence:0.9981986880302429> was absolutely decadent - - there was none of the stringiness that sometimes accompanies fair <sushi:Positive Confidence:0.696053683757782> - - this fish was perfect ! ! ! !
Example 168: plus , i am allergic to <rice:Neutral Confidence:0.9988677501678467> , and the <waitstaff:Positive Confidence:0.9993705153465271> was unbelievably accomodating - - did n ' t even bat an eye !
Example 169: and the <waiter:Neutral Confidence:0.9989742040634155> suggested a perfect <sake:Positive Confidence:0.999161958694458> ! !
Example 170: unbeatable <sushi:Positive Confidence:0.9995065927505493> !
Example 171: melt in your mouth <nigiri:Neutral Confidence:0.9989190101623535> and sashmi , and very tasty <rolls:Positive Confidence:0.9976761937141418> too .
Example 172: be sure to try the <oyster roll:Positive Confidence:0.9995552897453308> .
Example 173: – how to describe the <best:Positive Confidence:0.9972586631774902> sushi in nyc : hmmmm , delicious , amazing , fantastic , suculent , perfect , nah , all of the above .
Example 174: i ca n ' t saybenough good things about this <restaurant:Positive Confidence:0.9994097948074341> , and i ca n ' t wait for my next several visits .
Example 175: the best chuwam mushi i have ever had .
Example 176: good <sushi:Positive Confidence:0.9983848333358765> , high price
Example 177: one of the best <sushi:Positive Confidence:0.9995242357254028> place in town .
Example 178: the house special roll is really good .
Example 179: a cozy <spot:Positive Confidence:0.999476969242096> for Positive
Example 180: – i ca n ' t <believe:Positive Confidence:0.9988401532173157> murphy ' s has been around for over 25 years , amazing .
Example 181: brunch at murphy ' s is to die for , my specialty . . . <egg white omelet:Neutral Confidence:0.9686536192893982> , the <food:Positive Confidence:0.9962781071662903> is always freshly prepared .
Example 182: it ' s the perfect <spot:Positive Confidence:0.9995251893997192> for a romantic date for 2 or a secret rendezvous !
Example 183: save room for scrumptious <desserts:Positive Confidence:0.9994125366210938> .
Example 184: the restaurant offers an extensive <wine list:Positive Confidence:0.9974380731582642> and an <ambiance:Positive Confidence:0.9994136095046997> you wo n ' t forget !
Example 185: – best <mexican:Positive Confidence:0.9963443875312805> place <for:Positive Confidence:0.8985047340393066> lunch in the financial district .
Example 186: love the <enchiladas:Positive Confidence:0.9993463158607483> and <chicken soup:Positive Confidence:0.9995090961456299> - and be sure to check out their <specials:Positive Confidence:0.877544641494751> .
Example 187: the <cooks:Positive Confidence:0.7168573141098022> have been at the restaurant for years and cook family <recipes:Neutral Confidence:0.6564095616340637> .
Example 188: can get busy on fridays for a <table:Neutral Confidence:0.9988006353378296> but once seated , the <service:Positive Confidence:0.9994565844535828> is so efficient you can be in and out of there quickly .
Example 189: the <sushi:Positive Confidence:0.9995135068893433> was excellent and the <wait staff:Positive Confidence:0.9995664954185486> was quick .
Example 190: the <atmosphere:Neutral Confidence:0.9435452818870544> was just okay .
Example 191: space was limited , but the <food:Positive Confidence:0.9990615248680115> made up for it .
Example 192: well i guess it ' s hard to be seated when one is invisible to the <staff:Negative Confidence:0.9861141443252563> .
Example 193: we stood there for 10 minutes while <employees:Negative Confidence:0.9949439167976379> walked back and forth ignoring us .
Example 194: finally , my wife stood face to face in front of one of the <staff:Negative Confidence:0.9988186955451965> and she asked , " are you <waiting:Neutral Confidence:0.9976840019226074> for a <table:Neutral Confidence:0.9991663694381714> ? "
Example 195: the <caesar salad:Neutral Confidence:0.8397173881530762> i ordered had so much <lemon:Negative Confidence:0.9967079162597656> i could n ' t eat it .
Example 196: great <food:Positive Confidence:0.999474823474884> , better <margaritas:Positive Confidence:0.9994851350784302> !
Example 197: – this is one of my <top lunch:Neutral Confidence:0.8716978430747986> spots , <huge:Positive Confidence:0.9909932017326355> portions , <fast:Positive Confidence:0.9994858503341675> service and <amazing:Positive Confidence:0.999414324760437> margaritas ! !
Example 198: it gets really busy , so get there on the early side so you can grab a <seat:Neutral Confidence:0.9985530972480774> , if you do have to wait , its not bad because the <service:Positive Confidence:0.9986194372177124> is quick !
Example 199: check out the <art:Positive Confidence:0.9994763731956482> on the walls , very colorful !
Example 200: i love this <place:Positive Confidence:0.9994838237762451> !
Example 201: – i have been eating at this place for over 8 years now and i have never had one <bad:Positive Confidence:0.9994577765464783> meal .
Example 202: i highly recommend this place to all that want to try <indain food:Positive Confidence:0.9990398287773132> for the first time .
Example 203: the <lunch menu:Positive Confidence:0.999535322189331> is an awesome deal !
Example 204: plenty of <food:Positive Confidence:0.9993926286697388> , trust me .
Example 205: fresh <ingrediants:Positive Confidence:0.9994248151779175> and super tasty .
Example 206: best <food:Positive Confidence:0.9995098114013672> , phenominal service
Example 207: for the finicky <sushi:Neutral Confidence:0.9983630776405334> eater and those who have sampled the best nyc has to offer , the <fish:Positive Confidence:0.9995545744895935> is the freshest and the <service:Positive Confidence:0.9995287656784058> is superb .
Example 208: not only can the <selection:Positive Confidence:0.9992708563804626> be innovative , but there ' s a nice balance of traditional <sushi:Positive Confidence:0.9328514337539673> as well .
Example 209: the nicest <waiters:Positive Confidence:0.99951171875> in town .
Example 210: – <this:Negative Confidence:0.9991658926010132> place is unbelievably over - rated .
Example 211: if i want to stand in line on sunday for an hour to get average <brunch food:Neutral Confidence:0.9892593622207642> , then i would put murphy ' s at the top of the list .
Example 212: the regular <menu:Neutral Confidence:0.9986911416053772> here is slightly above average that is not worth the snotty <attitude:Negative Confidence:0.999243974685669> that you receive .
Example 213: your a <sushi:Positive Confidence:0.7929739952087402> fan , you love expertly cut fish , great <sake:Positive Confidence:0.9977389574050903> , a killer <soho location:Positive Confidence:0.9982815980911255> , and of course : <salmon:Neutral Confidence:0.9958761930465698> , tuna , fluke , <yellow tail:Neutral Confidence:0.9976828098297119> , <cod:Neutral Confidence:0.9955565333366394> , <mackeral:Neutral Confidence:0.995719850063324> , <jellyfish:Neutral Confidence:0.9926003813743591> , <sea urchin:Neutral Confidence:0.9925959706306458> , <shrimp:Neutral Confidence:0.9925472140312195> , <lobster:Neutral Confidence:0.9922177791595459> , <sea bream:Neutral Confidence:0.9925268888473511> , <trout:Neutral Confidence:0.9913954138755798> , milk fish , <blue fin tuna:Neutral Confidence:0.9947675466537476> , <eel:Neutral Confidence:0.9934631586074829> , <crab:Neutral Confidence:0.9947691559791565> , <sardine:Neutral Confidence:0.9959264993667603> , <monk fish:Neutral Confidence:0.9904173612594604> , <roe:Neutral Confidence:0.9916669726371765> , <scallop:Neutral Confidence:0.9698216319084167> , <oysters:Neutral Confidence:0.894161581993103> , and a varity of toro .
Example 214: your a <sushi:Positive Confidence:0.8175867199897766> fan , you love expertly cut fish , great <sake:Positive Confidence:0.997606635093689> , a killer <soho location:Positive Confidence:0.9978687763214111> , and of course : <salmon:Neutral Confidence:0.9958772659301758> , tuna , fluke , <yellow tail:Neutral Confidence:0.9982738494873047> , <cod:Neutral Confidence:0.9977626800537109> , <mackeral:Neutral Confidence:0.997905969619751> , jelly $ t $ , <sea urchin:Neutral Confidence:0.9961056113243103> , <shrimp:Neutral Confidence:0.995287299156189> , <lobster:Neutral Confidence:0.9944586753845215> , <sea bream:Neutral Confidence:0.9940476417541504> , <trout:Neutral Confidence:0.9926155805587769> , milk fish , <blue fin tuna:Neutral Confidence:0.9946759939193726> , <eel:Neutral Confidence:0.9933333992958069> , <crab:Neutral Confidence:0.9945764541625977> , <sardine:Neutral Confidence:0.995703399181366> , <monk fish:Neutral Confidence:0.989692747592926> , <roe:Neutral Confidence:0.9901703000068665> , <scallop:Neutral Confidence:0.9624527096748352> , <oysters:Neutral Confidence:0.8653944134712219> , and a varity of toro .
Example 215: there is only one <place:Positive Confidence:0.9994257688522339> on the east coast that has it all , plus a lot more .
Example 216: bring your cell phone cause you may have to wait to get into the best <sushi:Positive Confidence:0.9987421631813049> restaurant in the world : blue ribbon sushi .
Example 217: hands down , the best <tuna:Positive Confidence:0.9995228052139282> i have ever had .
Example 218: blue ribbon lives up to it ' s fantastic reputation .
Example 219: great value <sushi:Positive Confidence:0.9926440119743347> with high quality & nice <setting:Positive Confidence:0.9994990825653076> .
Example 220: try the <chef:Neutral Confidence:0.9905477166175842> ' s choice for <sushi:Neutral Confidence:0.9535788297653198> as the <smoked yellowtail:Positive Confidence:0.9994644522666931> was incredible and the <rolls:Positive Confidence:0.9990279674530029> were also tasty .
Example 221: poor customer service / poor <pizza:Negative Confidence:0.999129593372345> .
Example 222: poor customer service / poor <pizza:Negative Confidence:0.999129593372345> .
Example 223: – as with most restaurants in seattle , mioposto ' <s:Negative Confidence:0.9879504442214966> service was bad and <the:Negative Confidence:0.9957004189491272> food was overpriced .
Example 224: i know many people have their favorite types of <pizza:Positive Confidence:0.9111851453781128> and pizza <places:Positive Confidence:0.6714553833007812> , but mioposto ' s pizza lacks <quality:Negative Confidence:0.9850552082061768> and good <taste:Negative Confidence:0.9832823872566223> .
Example 225: to be honest , i ' ve had better frozen <pizza:Positive Confidence:0.9689580202102661> .
Example 226: the only positive thing about mioposto is the nice <location:Positive Confidence:0.9995067119598389> .
Example 227: i was frankly shocked when i read the bad reviews - this <place:Positive Confidence:0.9993010759353638> is fantastic ; it has not let us down in any way , and we ' ve eaten here more than 10 times .
Example 228: the <food:Positive Confidence:0.9994357228279114> is fantastic , and the <waiting staff:Positive Confidence:0.9995427131652832> has been perfect every single time we ' ve been there .
Example 229: the only problem would be the <wait:Negative Confidence:0.9939336180686951> , but we usually just have a <drink:Neutral Confidence:0.9987408518791199> in the front while waiting .
Example 230: seafood plus
Example 231: the <appetizer of oysters:Positive Confidence:0.9848692417144775> , <lobster:Neutral Confidence:0.8960690498352051> , crab ( small size ) made a perfect <entre:Positive Confidence:0.9882072806358337> for my wife .
Example 232: seabass on lobster risotto was the best .
Example 233: caesar salad was superb .
Example 234: great <bottle of wine:Positive Confidence:0.9995033740997314> .
Example 235: leave room for <dessert:Positive Confidence:0.8229293823242188> .
Example 236: the food was ok , but the <service:Negative Confidence:0.9861444234848022> was so poor that the food was cold buy the time everyone in my party was <served:Negative Confidence:0.8754737973213196> .
Example 237: we had a very hard time getting the <waitress:Negative Confidence:0.9977699518203735> ' attention and finally had to get up and go inside to speak to a <manager:Neutral Confidence:0.9953195452690125> .
Example 238: as it turns out the <owner:Negative Confidence:0.9663660526275635> was seated right next to us and when he came over to check on our problems was very dismissive and offered a token 20 % discount on our <bill:Neutral Confidence:0.9989417195320129> .
Example 239: avoid the place
Example 240: when i got there i sat up stairs where the <atmosphere:Positive Confidence:0.9976125955581665> was cozy & the <service:Negative Confidence:0.9982984662055969> was horrible !
Example 241: i waited for 10 - 15 minutes for <service:Negative Confidence:0.9741093516349792> ordered a <beer:Neutral Confidence:0.9754378199577332> & was never <served:Negative Confidence:0.7955166101455688> again .
Example 242: i went home & looked them up online again where i discovered there is a link for a give away that does n ' t work so emailed the restaurant about the non existent <service:Negative Confidence:0.9985307455062866> & deceptive link .
Example 243: after sitting at the bar for over 20 minutes the <bar keep:Negative Confidence:0.9980602860450745> had made only 2 <drinks:Neutral Confidence:0.9990468621253967> & kept telling us she ' d be right with us .
Example 244: we left without ever getting <service:Negative Confidence:0.9992552399635315> .
Example 245: best <crab cakes:Positive Confidence:0.9995169639587402> in town
Example 246: – that s a big statement considering i ' ve been <pulling crab:Neutral Confidence:0.9989898800849915> traps and making <the:Neutral Confidence:0.9990450739860535> cakes myself since i was about seven - but something about these little devils gets better every time .
Example 247: if you can , come to this <place:Negative Confidence:0.7725690007209778> by boat and make it a whole evening .
Example 248: great seasonal <fish:Positive Confidence:0.9993830919265747> and <seafood:Positive Confidence:0.9991224408149719> , with a classy <waterfront setting:Positive Confidence:0.9993976354598999> .
Example 249: great <pizza:Positive Confidence:0.9975770115852356> , poor service
Example 250: – love <their:Positive Confidence:0.9994082450866699> pizza , especially <the mushroom:Positive Confidence:0.9995662569999695> pizza .
Example 251: – love <their:Positive Confidence:0.9994082450866699> pizza , especially <the mushroom:Positive Confidence:0.9995662569999695> pizza .
Example 252: also love their caeser salad .
Example 253: prefer to order it and pick it up though because i do n ' t like the <servers:Negative Confidence:0.9991395473480225> , one young woman in particular .
Example 254: management should really take notice and train their <waitstaff:Neutral Confidence:0.7642578482627869> and teach them some proper manners .
Example 255: many people talk about the great <pizza:Positive Confidence:0.8642205595970154> and poor <service:Negative Confidence:0.990708589553833> , so it ca n ' t just be the rantings of a few dissatisfied customers .
Example 256: it ' s a great little <place:Positive Confidence:0.9990278482437134> with tons of potential to be a neighborhood joint if the <service:Negative Confidence:0.9869440793991089> were n ' t so impersonal and corporate - like .
Example 257: great breakfast
Example 258: – <this:Neutral Confidence:0.9982132911682129> place is famous for <their:Positive Confidence:0.9994407296180725> breakfast .
Example 259: the <food:Positive Confidence:0.999322772026062> is great and they make a mean bloody mary .
Example 260: i love <breakfast:Positive Confidence:0.9994803071022034> here .
Example 261: their crab eggs benedict is addicting .
Example 262: all their <menu items:Positive Confidence:0.9995129108428955> are a hit , and they serve <mimosas:Neutral Confidence:0.9989516735076904> .
Example 263: best <chinese food:Positive Confidence:0.9995070695877075> i have tasted in a long time
Example 264: the <ambiance:Positive Confidence:0.999316930770874> of the restaurant was nice and good for fine <dinning:Positive Confidence:0.9994478821754456> .
Example 265: the <staff:Positive Confidence:0.9994714856147766> was very nice and courteous and obviously chinese .
Example 266: so about the <prawns:Positive Confidence:0.9992799162864685> , they were fresh and had a slight crispiness about the batter . . . soooo good . . . the <walnuts:Positive Confidence:0.9398891925811768> were cut in smaller pieces and very crunchy and tasty .
Example 267: best honey walnyt prawns that we have every tasted .
Example 268: the <brocollis:Positive Confidence:0.9995185136795044> were so fresh and tasty .
Example 269: i would normally not finish the brocolli when i order these kinds of <food:Neutral Confidence:0.9990034699440002> but for the first time , every piece was as eventful as the first one . . . the <scallops and prawns:Positive Confidence:0.9992228746414185> was so fresh and nicely cooked .
Example 270: for <desert:Neutral Confidence:0.999171257019043> we had the mango ginger creme <brulee:Positive Confidence:0.9984884262084961> . . . oh la la yummy ! ! !
Example 271: we are for sure coming back to this <restaurant:Positive Confidence:0.9993855953216553> .
Example 272: chintzy portions
Example 273: – <the:Positive Confidence:0.995964765548706> sushi here is perfectly good , but for $ 5 a piece , either <the slices of:Negative Confidence:0.9981480836868286> fish should be larger , or there should be no pretense that this is a <moderately:Positive Confidence:0.6998486518859863> priced restaurant ( even for nyc ) .
Example 274: i ' m astonished that this restaurant is categorized <as $ $:Negative Confidence:0.9984416365623474> $ rather than $ $ $ $ .
Example 275: terrible <service:Negative Confidence:0.7353649139404297> , <food:Positive Confidence:0.7816380858421326> ok , pricey
Example 276: in other words , if they are n ' t making $ $ off of you then you do n ' t rate high on their ' <service:Negative Confidence:0.9261487722396851> scale ' .
Example 277: food wise , its ok but a bit pricey for what you get considering the restaurant is n ' t a fancy <place:Negative Confidence:0.8833043575286865> .
Example 278: if i needed to name some they would include the location to the beach or golden gate park .
Example 279: another plus is the open <feel:Positive Confidence:0.999530553817749> of the restaurant with glass walls on all sides .
Example 280: amazing spanish <mackeral special appetizer:Positive Confidence:0.999233603477478> and perfect <box sushi:Positive Confidence:0.9990320205688477> ( that <eel with avodcao:Neutral Confidence:0.9009906053543091> - - um um um ) .
Example 281: as usual the omikase did n ' t disappoint in freshness , although it scored low on <creativity:Negative Confidence:0.9987288117408752> and <selection:Negative Confidence:0.9984246492385864> .
Example 282: their <specialty rolls:Positive Confidence:0.998042106628418> are impressive , though i ca n ' t remember what we had .
Example 283: great selection of <sakes:Positive Confidence:0.9995067119598389> .
Example 284: green tea <creme:Positive Confidence:0.9985837936401367> brulee gets better each time i have it .
Example 285: it is n ' t the cheapest <sushi:Negative Confidence:0.9785822033882141> but has been worth it every time .
Example 286: very poor <customer service:Negative Confidence:0.9994204044342041> .
Example 287: – schooner or later ' s <charming:Positive Confidence:0.9986851811408997> location along the marina in long beach and <average:Neutral Confidence:0.9809998273849487> food does not , unfortunately , compensate for its very poor <customer:Negative Confidence:0.9799757599830627> service .
Example 288: while this <diner:Neutral Confidence:0.9978779554367065> had reasonably good <food:Negative Confidence:0.7287617921829224> , the restaurant <staff:Negative Confidence:0.9989068508148193> seemed completely indifferent to our presence , and this attitude was reflected in the lack of <service:Negative Confidence:0.995307981967926> .
Example 289: after one member of our party had been bumped repeatedly by a <waitress:Negative Confidence:0.8158661127090454> , a polite request that he not be bumped sent the waitress into an abusive rant .
Example 290: a brief conversation with the <manager:Negative Confidence:0.9993489384651184> at the end of the <meal:Neutral Confidence:0.9989964365959167> was the greatest disappointment - - to say we had been " blown off " would be an understatement .
Example 291: the <manager:Negative Confidence:0.9970859885215759> continually interrupted with " is there anything else i can do for you ? " , a strange comment because she had hardly listened , let alone responded to our expression of disappointment at our experience .
Example 292: you are with a hot date and he / she has an urge for <sushi:Neutral Confidence:0.6490190625190735> . . . then this might be the place .
Example 293: the <fish:Positive Confidence:0.9994035959243774> was fresh , though it was cut very thin .
Example 294: great <service:Positive Confidence:0.9990895986557007> .
Example 295: good <sake:Positive Confidence:0.9983574748039246> selection .
Example 296: dungeness crabs here !
Example 297: – ray ' s is the place to go for high <quality seafood:Positive Confidence:0.9995772242546082> dinners .
Example 298: we were only in seattle for one night and i ' m so glad we picked rays for <dinner:Neutral Confidence:0.9488168358802795> !
Example 299: i love <dungeness crabs:Positive Confidence:0.9991586208343506> and at ray ' s you can get them <served:Positive Confidence:0.9651947617530823> in about 6 different ways !
Example 300: we shared the <family platter:Neutral Confidence:0.9991968274116516> and i especially enjoyed the <black:Positive Confidence:0.9948989748954773> cod in sake kasu .
Example 301: i ended the <meal:Neutral Confidence:0.9988675117492676> with the unusual <dessert:Positive Confidence:0.6062542200088501> of a <port:Neutral Confidence:0.649896502494812> and chocolate tasting . . . . yummy !
Example 302: and the <service:Positive Confidence:0.9993834495544434> was simply spendid - quite a delight .
Example 303: – <great:Positive Confidence:0.9991598129272461> drinks <, corn beef:Positive Confidence:0.9988240599632263> hash <,:Positive Confidence:0.9990966320037842> coffee , b fast burritos , gluten free menu .
Example 304: the <service:Positive Confidence:0.9994799494743347> is fantastic at this fun <place:Positive Confidence:0.9995108842849731> .
Example 305: if there is a line very day of the week for the entire time a <place:Positive Confidence:0.8517894148826599> is open , you know it is great .
Example 306: best neighborhood standby .
Example 307: in grammercy / union square / east village this is my neighbors and my favorite <spot:Positive Confidence:0.9994955062866211> .
Example 308: the <music:Positive Confidence:0.9992496371269226> is great , no night better or worse , the <bar tenders:Positive Confidence:0.5945984721183777> are generous with the pouring , and the lighthearted <atmosphere:Positive Confidence:0.998043417930603> will lifts you spirits .
Example 309: oh , and the <cheese fries:Positive Confidence:0.9995338916778564> are awesome !
Example 310: good <food:Positive Confidence:0.9987848401069641> , great <service:Positive Confidence:0.9990684390068054> , average <prices:Neutral Confidence:0.9738725423812866> ( for the strip )
Example 311: – i decided to eat at stack because of <their:Positive Confidence:0.7679176330566406> price fixed pre <- show:Positive Confidence:0.5450234413146973> dinner .
Example 312: when i walked in , i was taken aback by their incredible <wood decor:Positive Confidence:0.999550998210907> .
Example 313: the music playing was very hip , 20 - 30 something pop music , but the <subwoofer:Negative Confidence:0.9829923510551453> to the sound system was located under my seat , which became annoying midway through <dinner:Neutral Confidence:0.9884418845176697> .
Example 314: i got the shellfish and <shrimp:Neutral Confidence:0.9662073254585266> appetizer and it was alright .
Example 315: it was n ' t the freshest <seafood:Negative Confidence:0.9989809393882751> ever , but the <taste:Positive Confidence:0.9622649550437927> and presentation was ok .
Example 316: i picked the <asparagus:Positive Confidence:0.9715762734413147> , which turned out to be incredible and perfectly prepared .
Example 317: the 9 oz <steak:Positive Confidence:0.8489173054695129> came next and it tasted great , at least initially .
Example 318: the <steak:Positive Confidence:0.9994331002235413> was done to my exact liking ( medium rare ) and was nice and juicy .
Example 319: it ? s <served:Neutral Confidence:0.8216696381568909> with either a peppercorn sauce or <red wine reduction:Neutral Confidence:0.9952604174613953> , though both were indistinguishable in <taste:Negative Confidence:0.7206714153289795> .
Example 320: though , one thing i realized later on was that the restaurant either used <msg:Negative Confidence:0.7709355354309082> or a <meat tenderizer:Neutral Confidence:0.9373965263366699> on the <steak:Neutral Confidence:0.9986067414283752> .
Example 321: the <desert:Positive Confidence:0.9989016056060791> was the perfect ending to an almost perfect <dinner:Positive Confidence:0.9910078644752502> .
Example 322: but the <servers:Positive Confidence:0.9995108842849731> were extremely attentive and very friendly .
Example 323: overall , i would go back and eat at the restaurant again .
Example 324: good <sake:Positive Confidence:0.998672366142273> , good <food:Positive Confidence:0.9990772008895874> – i honestly do n ' t know much about japanese food at all .
Example 325: server made several <sake:Positive Confidence:0.9900745749473572> suggestions which were very good .
Example 326: had many <dishes:Neutral Confidence:0.9860149621963501> but the best was the <lobster:Positive Confidence:0.9991846680641174> 3 ways .
Example 327: the <waiter:Negative Confidence:0.9976882934570312> was a bit unfriendly and the feel of the restaurant was crowded .
Example 328: also , there was only one <bathroom stall:Neutral Confidence:0.5369933247566223> - probably need more for such big <crowds:Negative Confidence:0.9956133365631104> .
Example 329: most importantly , we were so excited about the <food:Neutral Confidence:0.9617336988449097> after seeing the very creative <menu:Positive Confidence:0.9993100166320801> .
Example 330: at best , the <food:Positive Confidence:0.9872221350669861> was good and definately overpriced .
Example 331: for the amount of <food:Neutral Confidence:0.5953931212425232> we got the <prices:Negative Confidence:0.99856036901474> should have been lower .
Example 332: my favortie <pizza:Positive Confidence:0.9994938373565674> joint in seattle
Example 333: – this is my <":Positive Confidence:0.9988449811935425> must bring out of town guests to " restaurant and they always enjoy and rave about it .
Example 334: the <pizza:Positive Confidence:0.9995149374008179> is delicious and the <salads:Positive Confidence:0.9995242357254028> are fantastic .
Example 335: i ' ve always found the <wait staff:Positive Confidence:0.8690404295921326> and , if you sit at the <bar:Neutral Confidence:0.9980446100234985> , the <cooks:Positive Confidence:0.9986048340797424> very friendly .
Example 336: i also really enjoy the simplicity of the <decor:Positive Confidence:0.9988589286804199> and intimate feeling of a small restaurant .
Example 337: – my husband and i <love:Positive Confidence:0.9992437362670898> eating at mioposto caf é .
Example 338: we ’ re ca n ’ t say enough about their delicious <gourmet pizza:Positive Confidence:0.9995211362838745> ’ s !
Example 339: you wo n ’ t be disappointed by their <menu:Positive Confidence:0.9622135162353516> .
Example 340: the <pizza:Positive Confidence:0.994318425655365> ’ s are thin <crust:Positive Confidence:0.9509528279304504> and the <menu:Neutral Confidence:0.8046694397926331> offers very creative combinations and <toppings:Positive Confidence:0.9944185018539429> .
Example 341: the <pizza:Positive Confidence:0.9987026453018188> ’ s are light and scrumptious .
Example 342: try the <pizza:Positive Confidence:0.8668277859687805> ensalata !
Example 343: the <pizza:Negative Confidence:0.9341416358947754> ’ s are not huge and the <crust:Positive Confidence:0.9987506866455078> is thin … keep that in mind when you ’ re ordering .
Example 344: the <food:Positive Confidence:0.9994822144508362> is sinful .
Example 345: the <staff:Positive Confidence:0.9994339346885681> was really friendly .
Example 346: the <atmosphere:Positive Confidence:0.9994877576828003> was great .
Example 347: the specialty here is decadent <pancakes:Positive Confidence:0.9783073663711548> , but i ' ve been back now four times , and i ' ve been wowed every time .
Example 348: nothing on the <menu:Negative Confidence:0.6312589049339294> is less than amazing .
Example 349: go with some friends , wait the half hour or so with a <cup:Neutral Confidence:0.999221920967102> of <joe:Neutral Confidence:0.998945415019989> , and enjoy more than your average <breakfast:Positive Confidence:0.9989448189735413> .
Example 350: good <eats:Positive Confidence:0.9995142221450806> .
Example 351: i do n ' t know why anyone would want to write a great review about this <place:Negative Confidence:0.8960394263267517> .
Example 352: i have been to this <place:Negative Confidence:0.9991974234580994> , folks and it is bad .
Example 353: maybe it is good for that one night once in a blue moon when the <chefs:Neutral Confidence:0.9937076568603516> decide to use <fish:Neutral Confidence:0.6730204224586487> that ' s half - way decent .
Example 354: i have been here , spent tons of <money:Negative Confidence:0.9845513701438904> on a <chef special dinner:Negative Confidence:0.7466579675674438> and it was a major dissappointment .
Example 355: fancy pieces of <exotic fish:Positive Confidence:0.9860572814941406> on a $ 100 dollar <plate:Neutral Confidence:0.8446521759033203> and not one was eatable .
Example 356: – <the:Positive Confidence:0.9994062185287476> atmosphere is great for any special occasion you might want to celebrate .
Example 357: the best <dish:Positive Confidence:0.9993839263916016> are the honwy walnut prawns - just outstanding .
Example 358: the <service:Positive Confidence:0.9994668364524841> is really attentive and charming .
Example 359: the <service:Positive Confidence:0.9993205070495605> was excellent , the <coffee:Positive Confidence:0.9994311928749084> was good even by starbucks standards and the <food:Positive Confidence:0.9993914365768433> was outstanding .
Example 360: – i recently had the pleasure <of:Positive Confidence:0.9995284080505371> dining as this delightful restaurant on 2nd street and wow what a great evening we had .
Example 361: the <food:Positive Confidence:0.9995211362838745> is fantastic , authentic , delicious and very , very affordable .
Example 362: the <decor:Positive Confidence:0.9995392560958862> was beautiful and unique .
Example 363: there was a really nice <vibe:Positive Confidence:0.9966002106666565> about the <place:Positive Confidence:0.9600010514259338> . . . good <music:Positive Confidence:0.9993559718132019> , <atmosphere:Positive Confidence:0.9995163679122925> and happy looking <people:Positive Confidence:0.9995238780975342> .
Example 364: our <server:Positive Confidence:0.9995244741439819> was very professional and friendly .
Example 365: to the <owners:Positive Confidence:0.9982346296310425> of <open sesame:Neutral Confidence:0.6071572303771973> . . . bravo . . . i ca n ' t wait to come back to dine at your restaurant !
Example 366: it ' s a tiny <place:Negative Confidence:0.9293291568756104> so if you get there before 8 pm on a weekend ( thurs ? sun ) you will find it easier to get a table or a seat at the <sushi bar:Neutral Confidence:0.9984897375106812> .
Example 367: everything , and i mean everything on the <menu:Positive Confidence:0.9988679885864258> is delectable .
Example 368: the <waiters:Positive Confidence:0.9987422823905945> are very experienced and helpful with pairing your <drink:Neutral Confidence:0.9991288781166077> choice to your <food:Neutral Confidence:0.9992709755897522> tastes or vice versa .
Example 369: the <sushi:Positive Confidence:0.9993519186973572> is as fresh as it comes ? you ' d think ocean was in their backyard , no joke !
Example 370: if you ' re interested in good tasting ( without the <fish:Neutral Confidence:0.997494101524353> taste or smell ) , large <portions:Positive Confidence:0.9866963028907776> and creative <sushi dishes:Positive Confidence:0.999534010887146> this is your place . . .
Example 371: big thick pepperoni
Example 372: – <the:Positive Confidence:0.6376473307609558> pepperoni ' s cut real thick - - yum .
Example 373: the <pizza:Neutral Confidence:0.7601072192192078> itself is not exactly the best i ' ve had ever , but still pretty good .
Example 374: sit in the balcony
Example 375: food was good and appetizing .
Example 376: portions was just enough for me , but may not be for a big eater .
Example 377: fair <menu:Positive Confidence:0.8985939621925354> selection .
Example 378: the <appetizer:Positive Confidence:0.9993064403533936> was interesting , but the <creme brulee:Positive Confidence:0.9956185221672058> was very savory and delicious .
Example 379: indoor ambience was modern .
Example 380: if it ' s nice outside , request for a <table:Positive Confidence:0.8463327288627625> in the <balcony:Neutral Confidence:0.7201805114746094> .
Example 381: it ' s a great <place:Positive Confidence:0.9992300271987915> to people watch .
Example 382: although the <service:Negative Confidence:0.9961138963699341> could be improved considering the money you put in .
Example 383: our <drinks:Neutral Confidence:0.7026894688606262> kept coming but our <server:Negative Confidence:0.9990633130073547> came by a couple times .
Example 384: late night dinning with exeptional <food:Positive Confidence:0.9993771910667419> .
Example 385: we were <seated:Positive Confidence:0.9993718266487122> right away , the <table:Positive Confidence:0.9994426369667053> was private and nice .
Example 386: the <service:Positive Confidence:0.9958882927894592> was exceptional - sometime there was a feeling that we were served by the army of friendly <waiters:Positive Confidence:0.9953851103782654> .
Example 387: the <food:Positive Confidence:0.9994165897369385> was very good , <filet mignon:Positive Confidence:0.9994957447052002> was probably the best i ' ve ever try .
Example 388: the <portions:Positive Confidence:0.9991106390953064> are big though , so do not order too much .
Example 389: groovy <music:Positive Confidence:0.9832041263580322> made the <dinner:Neutral Confidence:0.9984813332557678> casual .
Example 390: i have a but here - there was a <bathroom attendant:Negative Confidence:0.9731176495552063> in the restroom which was odd .
Example 391: the <bathroom:Negative Confidence:0.8785225749015808> itself is very small with two <toilets:Neutral Confidence:0.7465387582778931> and only one <sink:Negative Confidence:0.9687321186065674> , the girl was staying totally on the way hanging out paper <towels:Negative Confidence:0.7734652161598206> from the <dispenser:Negative Confidence:0.5790677070617676> .
Example 392: this <place:Positive Confidence:0.9995008707046509> rocks ! !
Example 393: – mercedes restaurant is so tasty , <the:Positive Confidence:0.9994710087776184> service is undeniably awesome !
Example 394: the <chips and salsa:Positive Confidence:0.9995424747467041> are so yummy , and the <prices:Positive Confidence:0.9994476437568665> are fabulous .
Example 395: the <atmosphere:Positive Confidence:0.9977966547012329> is aspiring , and the <decor:Positive Confidence:0.9994189739227295> is festive and amazing . .
Example 396: the <catering:Positive Confidence:0.9995076656341553> is out of this world , and raouls <chicken vegetable soup:Positive Confidence:0.9994027614593506> rocks my world ! ! !
Example 397: drinks are suberb , and i feel like i am in a third world country when i walk in the door .
Example 398: - mediocre <service:Neutral Confidence:0.9929303526878357> / quality
Example 399: the presentation of snooze is excellent and it is one of those places that you feel more sophisticated just for being there ; but peel back the layers and you have an overpriced <ihop:Negative Confidence:0.9951761960983276> with a high brow <menu:Negative Confidence:0.7155869007110596> .
Example 400: to start off , approximately 8 - 10 oz of <orange juice:Neutral Confidence:0.9318297505378723> will <cost:Negative Confidence:0.7048162817955017> you $ 3 .
Example 401: they <serve:Negative Confidence:0.8474224805831909> it in a tall , skinny hour - <glass:Negative Confidence:0.8286852836608887> shaped glass to disguise the fact that you a getting a small juice at the <price:Neutral Confidence:0.9556460976600647> of a half gallon in a supermarket .
Example 402: i should have just asked for the <check:Neutral Confidence:0.9991372227668762> when i saw that ; but their <menu:Positive Confidence:0.9991689920425415> was so unique that i continued .
Example 403: the <pancakes:Positive Confidence:0.6409818530082703> were certainly inventive but $ 8 . 50 for 3 - 6 " pancakes ( one of them was more like 5 " ) in the <pancake:Positive Confidence:0.6372888684272766> flight ( sample of 3 different pancakes ) is well over - priced .
Example 404: the <pancakes:Negative Confidence:0.845134973526001> should be larger ( at least 8 " ) to justify the <expense:Neutral Confidence:0.9695382714271545> even with the unique offerings .
Example 405: on my meal i had to send back my <eggs:Negative Confidence:0.995261549949646> for a simple request of breaking the <yokes:Negative Confidence:0.9980871677398682> before cooking , and would have had to send them back again if i had n ' t rejected the meal all together .
Example 406: i rejected it because in the process of attempting to fix the <eggs:Negative Confidence:0.9992089867591858> they broke something else in the <dish:Neutral Confidence:0.9989545345306396> and i was too frustrated to continue .
Example 407: to their credit they removed the <dish:Neutral Confidence:0.9986862540245056> from the check ; but no <manager:Negative Confidence:0.9991334080696106> stopped by to ask what the problem was .
Example 408: in the end our <check:Neutral Confidence:0.9972398281097412> came to $ 27 for 4 small <pancakes:Negative Confidence:0.9039381742477417> , a <breakfast burrito:Neutral Confidence:0.9429887533187866> , an <orange juice:Neutral Confidence:0.9849721789360046> and an <iced tea:Neutral Confidence:0.9899216294288635> ( i had <water:Neutral Confidence:0.9978523254394531> ) .
Example 409: much more than just a great <view:Positive Confidence:0.9995417594909668> !
Example 410: – i am exceedingly pleased to report that <my:Positive Confidence:0.9995129108428955> dinner <at:Positive Confidence:0.9995112419128418> ray ' s boathouse last friday completely exceeded my expectations .
Example 411: ray ' s is something of a seattle institution , but given its gorgeous <sound views:Positive Confidence:0.9990211725234985> , i had suspected that the accolades were more due to the <scenery:Neutral Confidence:0.9645717740058899> than to the <food:Neutral Confidence:0.9659597277641296> and <service:Neutral Confidence:0.9429661631584167> .
Example 412: imagine my happy surprise upon finding that the <views:Positive Confidence:0.9991414546966553> are only the third - best thing about ray ' s !
Example 413: to start things off , our lovely <server:Positive Confidence:0.9993088245391846> brooke was quickly on hand to take my <drink:Neutral Confidence:0.9992873072624207> order .
Example 414: my party of two was feeling particularly ambitious , and we splurged on the shilshole sampler . . . a beautiful <assortment:Positive Confidence:0.9680396914482117> of enormous <white gulf prawns:Positive Confidence:0.5582523345947266> , <smoked albacore tuna:Positive Confidence:0.5006489157676697> , ray ' s fantastic <manila clams seasoned with dill:Neutral Confidence:0.7021358609199524> , <scallops:Neutral Confidence:0.7425550222396851> in a tasty <soy dressing:Neutral Confidence:0.9104409217834473> , and a tiny pile of <dungeness crab:Neutral Confidence:0.9757413268089294> atop a sublime <butter sauce:Positive Confidence:0.9614577293395996> .
Example 415: for my entr & eacute ; e , i completely enjoyed the seared alaskan <sea scallops:Neutral Confidence:0.5509985685348511> complemented by chard , <artichoke hearts:Neutral Confidence:0.9991293549537659> , <fennel:Neutral Confidence:0.999106228351593> , and pecorino toscano .
Example 416: the <scallops:Positive Confidence:0.8491958379745483> are apparently cooked in a <black olive butter:Neutral Confidence:0.9990507960319519> which really makes them unique ( not to mention tasty ) .
Example 417: my friend enjoyed the grilled alaskan king <salmon:Neutral Confidence:0.8501957654953003> with delectable creamed washington russet potatoes and crisp green <beans:Positive Confidence:0.9994029998779297> .
Example 418: i had a taste of all three items on her <plate:Positive Confidence:0.9979975819587708> , and they were superb .
Example 419: our <server:Positive Confidence:0.998454213142395> continued to be attentive throughout the night , but i did remain puzzled by one issue : who thinks that ray ' s is an appropriate place to take young children for <dinner:Neutral Confidence:0.9989867806434631> ?
Example 420: all considered , i have to say that <ray ':Positive Confidence:0.9992276430130005> s boathouse is deserving of its title as a seattle institution .
Example 421: while i could have done without the youth who shared the evening with us , our wonderful <server:Positive Confidence:0.9992669224739075> and <food:Positive Confidence:0.99919193983078> made the experience a very positive one .
[12]:
[{'sentence': 'serves really good sushi .',
'IOB': ['B-ASP', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['serves', 'really', 'good', 'sushi', '.'],
'aspect': ['serves', 'sushi'],
'position': [[0, 3], [0, 3]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0004788661899510771, 0.6750665307044983, 0.3244546353816986],
[0.0002311569405719638, 0.007874456234276295, 0.9918943047523499]],
'confidence': [0.6750665307044983, 0.9918943047523499]},
{'sentence': 'not the biggest portions but adequate .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['not', 'the', 'biggest', 'portions', 'but', 'adequate', '.'],
'aspect': ['portions'],
'position': [[3]],
'sentiment': ['Negative'],
'probs': [[0.979500949382782, 0.00579943647608161, 0.014699668623507023]],
'confidence': [0.979500949382782]},
{'sentence': 'green tea creme brulee is a must !',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['green', 'tea', 'creme', 'brulee', 'is', 'a', 'must', '!'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': " – i ca n ' t say enough about this place .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'ca',
'n',
"'",
't',
'say',
'enough',
'about',
'this',
'place',
'.'],
'aspect': ['this'],
'position': [[10, 12]],
'sentiment': ['Positive'],
'probs': [[0.004319787956774235, 0.0002108124317601323, 0.9954694509506226]],
'confidence': [0.9954694509506226]},
{'sentence': 'it has great sushi and even better service .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['it',
'has',
'great',
'sushi',
'and',
'even',
'better',
'service',
'.'],
'aspect': ['sushi', 'service'],
'position': [[3, 7], [3, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0001937689958140254,
0.00026443967362865806,
0.9995418787002563],
[0.00020203898020554334, 0.000256925355643034, 0.9995410442352295]],
'confidence': [0.9995418787002563, 0.9995410442352295]},
{'sentence': 'the entire staff was extremely accomodating and tended to my every need .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'entire',
'staff',
'was',
'extremely',
'accomodating',
'and',
'tended',
'to',
'my',
'every',
'need',
'.'],
'aspect': ['staff'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00021370728791225702,
0.0002842977119144052,
0.9995019435882568]],
'confidence': [0.9995019435882568]},
{'sentence': "i ' ve been to this restaurant over a dozen times with no complaints to date .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
"'",
've',
'been',
'to',
'this',
'restaurant',
'over',
'a',
'dozen',
'times',
'with',
'no',
'complaints',
'to',
'date',
'.'],
'aspect': ['restaurant'],
'position': [[6]],
'sentiment': ['Positive'],
'probs': [[0.0004111092130187899,
0.0008572530932724476,
0.9987316727638245]],
'confidence': [0.9987316727638245]},
{'sentence': 'the owner is belligerent to guests that have a complaint .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'owner',
'is',
'belligerent',
'to',
'guests',
'that',
'have',
'a',
'complaint',
'.'],
'aspect': ['owner'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.9984574317932129,
0.001313613960519433,
0.00022897655435372144]],
'confidence': [0.9984574317932129]},
{'sentence': 'good food !',
'IOB': ['O', 'B-ASP', 'O'],
'tokens': ['good', 'food', '!'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0001815193536458537,
0.0003353985957801342,
0.9994831085205078]],
'confidence': [0.9994831085205078]},
{'sentence': 'this is a great place to get a delicious meal .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['this',
'is',
'a',
'great',
'place',
'to',
'get',
'a',
'delicious',
'meal',
'.'],
'aspect': ['meal'],
'position': [[9]],
'sentiment': ['Positive'],
'probs': [[0.00018572818953543901,
0.0002621533640194684,
0.9995520710945129]],
'confidence': [0.9995520710945129]},
{'sentence': 'the staff is pretty friendly .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'staff', 'is', 'pretty', 'friendly', '.'],
'aspect': ['staff'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00027117683202959597,
0.0002679945027921349,
0.9994608759880066]],
'confidence': [0.9994608759880066]},
{'sentence': 'the onion rings are great !',
'IOB': ['O', 'B-ASP', 'I-ASP', 'O', 'O', 'O'],
'tokens': ['the', 'onion', 'rings', 'are', 'great', '!'],
'aspect': ['onion rings'],
'position': [[1, 2]],
'sentiment': ['Positive'],
'probs': [[0.00017091090558096766,
0.00029272373649291694,
0.999536395072937]],
'confidence': [0.999536395072937]},
{'sentence': ' – i was highly disappointed in the food at pagoda .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', '[SEP]'],
'tokens': [' ',
'–',
'i',
'was',
'highly',
'disappointed',
'in',
'the',
'food',
'at',
'pagoda',
'.'],
'aspect': ['the'],
'position': [[7, 11]],
'sentiment': ['Negative'],
'probs': [[0.9986276626586914, 0.0010925440583378077, 0.000279750645859167]],
'confidence': [0.9986276626586914]},
{'sentence': 'the lemon chicken tasted like sticky sweet donuts and the honey walnut prawns , the few they actually give you . . . . . were not good .',
'IOB': ['O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'lemon',
'chicken',
'tasted',
'like',
'sticky',
'sweet',
'donuts',
'and',
'the',
'honey',
'walnut',
'prawns',
',',
'the',
'few',
'they',
'actually',
'give',
'you',
'.',
'.',
'.',
'.',
'.',
'were',
'not',
'good',
'.'],
'aspect': ['lemon chicken', 'honey walnut prawns'],
'position': [[1, 2, 10, 11, 12], [1, 2, 10, 11, 12]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.6290537714958191, 0.37053564190864563, 0.0004106000124011189],
[0.449164479970932, 0.5503287315368652, 0.0005067752790637314]],
'confidence': [0.6290537714958191, 0.5503287315368652]},
{'sentence': 'nice ambience , but highly overrated place .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['nice',
'ambience',
',',
'but',
'highly',
'overrated',
'place',
'.'],
'aspect': ['ambience', 'place'],
'position': [[1, 6], [1, 6]],
'sentiment': ['Positive', 'Negative'],
'probs': [[0.00020735316502396017,
0.00023733988928142935,
0.9995552897453308],
[0.9987647533416748, 0.0009376501548103988, 0.0002977072144858539]],
'confidence': [0.9995552897453308, 0.9987647533416748]},
{'sentence': 'worst service i ever had',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['worst', 'service', 'i', 'ever', 'had'],
'aspect': ['service'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.9989626407623291,
0.0007209523464553058,
0.0003163534856867045]],
'confidence': [0.9989626407623291]},
{'sentence': 'everyone that sat in the back outside agreed that it was the worst service we had ever received .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['everyone',
'that',
'sat',
'in',
'the',
'back',
'outside',
'agreed',
'that',
'it',
'was',
'the',
'worst',
'service',
'we',
'had',
'ever',
'received',
'.'],
'aspect': ['service'],
'position': [[13]],
'sentiment': ['Negative'],
'probs': [[0.9992260932922363, 0.000569070631172508, 0.0002049318718491122]],
'confidence': [0.9992260932922363]},
{'sentence': 'our waiter was non - existent and after our food finally arrived over an hour after we ordered , we were not given any water or utensils .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['our',
'waiter',
'was',
'non',
'-',
'existent',
'and',
'after',
'our',
'food',
'finally',
'arrived',
'over',
'an',
'hour',
'after',
'we',
'ordered',
',',
'we',
'were',
'not',
'given',
'any',
'water',
'or',
'utensils',
'.'],
'aspect': ['waiter', 'food'],
'position': [[1, 9], [1, 9]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9992457628250122, 0.0005372347659431398, 0.000217010427149944],
[0.00218052021227777, 0.9972600936889648, 0.0005594007088802755]],
'confidence': [0.9992457628250122, 0.9972600936889648]},
{'sentence': 'i complained to the manager , but he was not even apologetic .',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['i',
'complained',
'to',
'the',
'manager',
',',
'but',
'he',
'was',
'not',
'even',
'apologetic',
'.'],
'aspect': ['manager'],
'position': [[4]],
'sentiment': ['Negative'],
'probs': [[0.9988617897033691,
0.0009368026512674987,
0.0002014648780459538]],
'confidence': [0.9988617897033691]},
{'sentence': 'fabulous italian food !',
'IOB': ['O', 'O', 'B-ASP', 'O'],
'tokens': ['fabulous', 'italian', 'food', '!'],
'aspect': ['food'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00020802549261134118,
0.00026292295660823584,
0.9995290040969849]],
'confidence': [0.9995290040969849]},
{'sentence': ' – i highly recommend mioposto .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', '[SEP]'],
'tokens': [' ', '–', 'i', 'highly', 'recommend', 'mioposto', '.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'i am so happy to have a wonderful italian restaurant in my neighborhood .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'am',
'so',
'happy',
'to',
'have',
'a',
'wonderful',
'italian',
'restaurant',
'in',
'my',
'neighborhood',
'.'],
'aspect': ['restaurant'],
'position': [[9]],
'sentiment': ['Positive'],
'probs': [[0.00015179436013568193,
0.00031423382461071014,
0.999534010887146]],
'confidence': [0.999534010887146]},
{'sentence': 'the wine list is wonderful and the food reminds me of my recent trip to italy .',
'IOB': ['O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'wine',
'list',
'is',
'wonderful',
'and',
'the',
'food',
'reminds',
'me',
'of',
'my',
'recent',
'trip',
'to',
'italy',
'.'],
'aspect': ['wine list', 'food'],
'position': [[1, 2, 7], [1, 2, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00021229441335890442,
0.0002641308819875121,
0.9995235204696655],
[0.0001337597641395405, 0.0004926668480038643, 0.9993736147880554]],
'confidence': [0.9995235204696655, 0.9993736147880554]},
{'sentence': 'i love this restaurant',
'IOB': ['O', 'O', 'O', 'B-ASP'],
'tokens': ['i', 'love', 'this', 'restaurant'],
'aspect': ['restaurant'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.0004669523041229695,
0.00019812678510788828,
0.9993348717689514]],
'confidence': [0.9993348717689514]},
{'sentence': ' – i will never forget the amazing meal , service , and ambiance i experience at this restaurant .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'will',
'never',
'forget',
'the',
'amazing',
'meal',
',',
'service',
',',
'and',
'ambiance',
'i',
'experience',
'at',
'this',
'restaurant',
'.'],
'aspect': ['amazing', ',', 'and'],
'position': [[7, 9, 12, 19], [7, 9, 12, 19], [7, 9, 12, 19]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00026253069518134, 0.0002605599584057927, 0.999476969242096],
[0.00026280430029146373, 0.00024934191606007516, 0.9994877576828003],
[0.00023808771220501512, 0.0002536396204959601, 0.999508261680603]],
'confidence': [0.999476969242096, 0.9994877576828003, 0.999508261680603]},
{'sentence': 'the wine list is incredible and extensive and diverse , the food is all incredible and the staff was all very nice , good at their jobs and cultured .',
'IOB': ['O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'wine',
'list',
'is',
'incredible',
'and',
'extensive',
'and',
'diverse',
',',
'the',
'food',
'is',
'all',
'incredible',
'and',
'the',
'staff',
'was',
'all',
'very',
'nice',
',',
'good',
'at',
'their',
'jobs',
'and',
'cultured',
'.'],
'aspect': ['wine list', 'food', 'staff'],
'position': [[1, 2, 11, 17], [1, 2, 11, 17], [1, 2, 11, 17]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.0003673633618745953, 0.0002427013241685927, 0.9993898868560791],
[0.00016584656259510666, 0.0006490065716207027, 0.9991851449012756],
[0.0001932592858793214, 0.0005470498581416905, 0.9992597699165344]],
'confidence': [0.9993898868560791, 0.9991851449012756, 0.9992597699165344]},
{'sentence': 'i have not a bad thing to say about this place .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['i',
'have',
'not',
'a',
'bad',
'thing',
'to',
'say',
'about',
'this',
'place',
'.'],
'aspect': ['place'],
'position': [[10]],
'sentiment': ['Positive'],
'probs': [[0.0002635909477248788,
0.00025465767248533666,
0.9994818568229675]],
'confidence': [0.9994818568229675]},
{'sentence': 'the food was great !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the', 'food', 'was', 'great', '!'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00018665629613678902,
0.0003013498499058187,
0.9995119571685791]],
'confidence': [0.9995119571685791]},
{'sentence': "it ' s * very * reasonably priced , esp for the quality of the food .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['it',
"'",
's',
'*',
'very',
'*',
'reasonably',
'priced',
',',
'esp',
'for',
'the',
'quality',
'of',
'the',
'food',
'.'],
'aspect': ['priced', 'food'],
'position': [[7, 15], [7, 15]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0006177635514177382, 0.0002501681155990809, 0.9991320967674255],
[0.00030072356457822025, 0.30805346369743347, 0.6916458010673523]],
'confidence': [0.9991320967674255, 0.6916458010673523]},
{'sentence': 'i had the kafta plate and it was perfect .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['i',
'had',
'the',
'kafta',
'plate',
'and',
'it',
'was',
'perfect',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'finally a meal that you will remember for a long time !',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['finally',
'a',
'meal',
'that',
'you',
'will',
'remember',
'for',
'a',
'long',
'time',
'!'],
'aspect': ['meal'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.0002285176597069949,
0.00047249594354070723,
0.9992990493774414]],
'confidence': [0.9992990493774414]},
{'sentence': ' – in a age of incremental cost cutting in restaurants , its nice to see a place that bucks that trend , and just plain delivers high quality food and good service , period .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'in',
'a',
'age',
'of',
'incremental',
'cost',
'cutting',
'in',
'restaurants',
',',
'its',
'nice',
'to',
'see',
'a',
'place',
'that',
'bucks',
'that',
'trend',
',',
'and',
'just',
'plain',
'delivers',
'high',
'quality',
'food',
'and',
'good',
'service',
',',
'period',
'.'],
'aspect': ['quality', 'good'],
'position': [[28, 31, 35], [28, 31, 35]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002148494531866163, 0.0002638696751091629, 0.9995212554931641],
[0.00021499085414689034, 0.00024967125500552356, 0.9995354413986206]],
'confidence': [0.9995212554931641, 0.9995354413986206]},
{'sentence': 'this is the place to relax and enjoy the finest quality food the industry can offer .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['this',
'is',
'the',
'place',
'to',
'relax',
'and',
'enjoy',
'the',
'finest',
'quality',
'food',
'the',
'industry',
'can',
'offer',
'.'],
'aspect': ['food'],
'position': [[11]],
'sentiment': ['Positive'],
'probs': [[0.00015373513451777399,
0.00033473328221589327,
0.9995115995407104]],
'confidence': [0.9995115995407104]},
{'sentence': 'caution - its real food for people who love the best .',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['caution',
'-',
'its',
'real',
'food',
'for',
'people',
'who',
'love',
'the',
'best',
'.'],
'aspect': ['food'],
'position': [[4]],
'sentiment': ['Neutral'],
'probs': [[0.00037776591489091516, 0.6337648034095764, 0.36585742235183716]],
'confidence': [0.6337648034095764]},
{'sentence': 'i liked the atmosphere very much but the food was not worth the price .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'liked',
'the',
'atmosphere',
'very',
'much',
'but',
'the',
'food',
'was',
'not',
'worth',
'the',
'price',
'.'],
'aspect': ['atmosphere', 'food'],
'position': [[3, 8], [3, 8]],
'sentiment': ['Positive', 'Negative'],
'probs': [[0.00017544956062920392,
0.00034887384390458465,
0.9994756579399109],
[0.6525688171386719, 0.3470936715602875, 0.0003375766391400248]],
'confidence': [0.9994756579399109, 0.6525688171386719]},
{'sentence': 'i may not be a sushi guru but i can tell you that the food here is just okay and that there is not much else to it .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'may',
'not',
'be',
'a',
'sushi',
'guru',
'but',
'i',
'can',
'tell',
'you',
'that',
'the',
'food',
'here',
'is',
'just',
'okay',
'and',
'that',
'there',
'is',
'not',
'much',
'else',
'to',
'it',
'.'],
'aspect': ['sushi', 'food'],
'position': [[5, 14], [5, 14]],
'sentiment': ['Neutral', 'Neutral'],
'probs': [[0.12579551339149475, 0.8712786436080933, 0.0029258443973958492],
[0.025136107578873634, 0.9292333126068115, 0.04563063383102417]],
'confidence': [0.8712786436080933, 0.9292333126068115]},
{'sentence': "rice is too dry , tuna was n ' t so fresh either .",
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['rice',
'is',
'too',
'dry',
',',
'tuna',
'was',
'n',
"'",
't',
'so',
'fresh',
'either',
'.'],
'aspect': ['rice', 'tuna'],
'position': [[0, 5], [0, 5]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9948047995567322, 0.004126063548028469, 0.0010691364295780659],
[0.9943233728408813, 0.0033427500165998936, 0.0023339116014540195]],
'confidence': [0.9948047995567322, 0.9943233728408813]},
{'sentence': 'i have eaten here three times and have found the quality and variety of the fish to be excellent .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'have',
'eaten',
'here',
'three',
'times',
'and',
'have',
'found',
'the',
'quality',
'and',
'variety',
'of',
'the',
'fish',
'to',
'be',
'excellent',
'.'],
'aspect': ['quality', 'variety', 'fish'],
'position': [[10, 12, 15], [10, 12, 15], [10, 12, 15]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.0002631705137901008, 0.003740099025890231, 0.9959967136383057],
[0.0003140697081107646, 0.006795552093535662, 0.992890477180481],
[0.0003609462874010205, 0.11681827902793884, 0.8828207850456238]],
'confidence': [0.9959967136383057, 0.992890477180481, 0.8828207850456238]},
{'sentence': 'however , the value and service are both severely lacking .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['however',
',',
'the',
'value',
'and',
'service',
'are',
'both',
'severely',
'lacking',
'.'],
'aspect': ['value', 'service'],
'position': [[3, 5], [3, 5]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9926034808158875, 0.003100049216300249, 0.004296517930924892],
[0.9974547028541565, 0.0014431504532694817, 0.0011021889513358474]],
'confidence': [0.9926034808158875, 0.9974547028541565]},
{'sentence': 'furthermore , while the fish is unquestionably fresh , rolls tend to be inexplicably bland .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['furthermore',
',',
'while',
'the',
'fish',
'is',
'unquestionably',
'fresh',
',',
'rolls',
'tend',
'to',
'be',
'inexplicably',
'bland',
'.'],
'aspect': ['fish', 'rolls'],
'position': [[4, 9], [4, 9]],
'sentiment': ['Positive', 'Negative'],
'probs': [[0.0002565729955676943, 0.0002588429197203368, 0.999484658241272],
[0.9989215135574341, 0.0008561903377994895, 0.00022236646327655762]],
'confidence': [0.999484658241272, 0.9989215135574341]},
{'sentence': 'the service ranges from mediocre to offensive .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'service',
'ranges',
'from',
'mediocre',
'to',
'offensive',
'.'],
'aspect': ['service'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.9895910620689392,
0.010087716393172741,
0.00032122459379024804]],
'confidence': [0.9895910620689392]},
{'sentence': 'on a recent trip , our waiter was extremely dismissive , while no less than three staff members waited hand - and - foot on a pair of japanese girls seated nearby .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['on',
'a',
'recent',
'trip',
',',
'our',
'waiter',
'was',
'extremely',
'dismissive',
',',
'while',
'no',
'less',
'than',
'three',
'staff',
'members',
'waited',
'hand',
'-',
'and',
'-',
'foot',
'on',
'a',
'pair',
'of',
'japanese',
'girls',
'seated',
'nearby',
'.'],
'aspect': ['waiter', 'staff members'],
'position': [[6, 16, 17], [6, 16, 17]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9311105012893677, 0.06823280453681946, 0.0006567563395947218],
[0.999186098575592, 0.00039316591573879123, 0.00042075326200574636]],
'confidence': [0.9311105012893677, 0.999186098575592]},
{'sentence': 'freshest sushi – i love this restaurant .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['freshest', 'sushi', '–', 'i', 'love', 'this', 'restaurant', '.'],
'aspect': ['sushi'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00024044937163125724,
0.00022382632596418262,
0.9995357990264893]],
'confidence': [0.9995357990264893]},
{'sentence': 'freshest sushi – i love this restaurant .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['freshest', 'sushi', '–', 'i', 'love', 'this', 'restaurant', '.'],
'aspect': ['sushi'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00024044937163125724,
0.00022382632596418262,
0.9995357990264893]],
'confidence': [0.9995357990264893]},
{'sentence': 'they pay such detail to everything from miso soup to complex rolls .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['they',
'pay',
'such',
'detail',
'to',
'everything',
'from',
'miso',
'soup',
'to',
'complex',
'rolls',
'.'],
'aspect': ['miso soup', 'rolls'],
'position': [[7, 8, 11], [7, 8, 11]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0007539646467193961, 0.09526247531175613, 0.9039835929870605],
[0.050186071544885635, 0.025768307968974113, 0.9240456223487854]],
'confidence': [0.9039835929870605, 0.9240456223487854]},
{'sentence': 'the sashimi was the freshest and most tender i have ever tasted .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'sashimi',
'was',
'the',
'freshest',
'and',
'most',
'tender',
'i',
'have',
'ever',
'tasted',
'.'],
'aspect': ['sashimi'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00024259854399133474,
0.00025240046670660377,
0.9995050430297852]],
'confidence': [0.9995050430297852]},
{'sentence': 'their apps are all delicious .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['their', 'apps', 'are', 'all', 'delicious', '.'],
'aspect': ['apps'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0003386056050658226,
0.0003873620880767703,
0.9992740750312805]],
'confidence': [0.9992740750312805]},
{'sentence': 'the only drawback is that this place is really expensive and the portions are on the small side .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'only',
'drawback',
'is',
'that',
'this',
'place',
'is',
'really',
'expensive',
'and',
'the',
'portions',
'are',
'on',
'the',
'small',
'side',
'.'],
'aspect': ['place', 'portions'],
'position': [[6, 12], [6, 12]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9942002296447754, 0.005603482946753502, 0.00019622690160758793],
[0.9976645708084106, 0.0005749888368882239, 0.0017604099120944738]],
'confidence': [0.9942002296447754, 0.9976645708084106]},
{'sentence': 'but the space is small and lovely , and the service is helpful .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['but',
'the',
'space',
'is',
'small',
'and',
'lovely',
',',
'and',
'the',
'service',
'is',
'helpful',
'.'],
'aspect': ['space', 'service'],
'position': [[2, 10], [2, 10]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.02460782416164875, 0.0015716172056272626, 0.9738205671310425],
[0.00043702535913325846, 0.00026748600066639483, 0.9992954730987549]],
'confidence': [0.9738205671310425, 0.9992954730987549]},
{'sentence': ' – the food was not great & the waiters were rude .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'the',
'food',
'was',
'not',
'great',
'&',
'the',
'waiters',
'were',
'rude',
'.'],
'aspect': ['the', 'the'],
'position': [[2, 8, 12], [2, 8, 12]],
'sentiment': ['Neutral', 'Neutral'],
'probs': [[0.19773650169372559, 0.7998533844947815, 0.0024101303424686193],
[0.19773650169372559, 0.7998533844947815, 0.0024101303424686193]],
'confidence': [0.7998533844947815, 0.7998533844947815]},
{'sentence': 'great service',
'IOB': ['O', 'B-ASP'],
'tokens': ['great', 'service'],
'aspect': ['service'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0007279988494701684,
0.00021466925682034343,
0.9990573525428772]],
'confidence': [0.9990573525428772]},
{'sentence': 'my service was stellar !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['my', 'service', 'was', 'stellar', '!'],
'aspect': ['service'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00017642545572016388,
0.0004954055184498429,
0.9993281364440918]],
'confidence': [0.9993281364440918]},
{'sentence': 'the bus boy even spotted that my table was shaking a stabilized it for me .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'bus',
'boy',
'even',
'spotted',
'that',
'my',
'table',
'was',
'shaking',
'a',
'stabilized',
'it',
'for',
'me',
'.'],
'aspect': ['table'],
'position': [[7]],
'sentiment': ['Negative'],
'probs': [[0.9665725827217102, 0.03265250101685524, 0.0007748584030196071]],
'confidence': [0.9665725827217102]},
{'sentence': 'food was fine , with a some little - tastier - than - normal salsa .',
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['food',
'was',
'fine',
',',
'with',
'a',
'some',
'little',
'-',
'tastier',
'-',
'than',
'-',
'normal',
'salsa',
'.'],
'aspect': ['food'],
'position': [[0]],
'sentiment': ['Positive'],
'probs': [[0.00022592155437450856, 0.0324983187019825, 0.9672757387161255]],
'confidence': [0.9672757387161255]},
{'sentence': 'the food was great , the margaritas too but the waitress was too busy being nice to her other larger party than to take better care of my friend and me .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'food',
'was',
'great',
',',
'the',
'margaritas',
'too',
'but',
'the',
'waitress',
'was',
'too',
'busy',
'being',
'nice',
'to',
'her',
'other',
'larger',
'party',
'than',
'to',
'take',
'better',
'care',
'of',
'my',
'friend',
'and',
'me',
'.'],
'aspect': ['food', 'margaritas', 'waitress'],
'position': [[1, 6, 10], [1, 6, 10], [1, 6, 10]],
'sentiment': ['Positive', 'Neutral', 'Negative'],
'probs': [[0.00022376504784915596, 0.018786881119012833, 0.980989396572113],
[0.0006605701055377722, 0.8368481993675232, 0.16249127686023712],
[0.9979914426803589, 0.001116006402298808, 0.0008924871799536049]],
'confidence': [0.980989396572113, 0.8368481993675232, 0.9979914426803589]},
{'sentence': 'mama mia – i live in the neighborhood and feel lucky to live by such a great pizza place .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O'],
'tokens': ['mama',
'mia',
'–',
'i',
'live',
'in',
'the',
'neighborhood',
'and',
'feel',
'lucky',
'to',
'live',
'by',
'such',
'a',
'great',
'pizza',
'place',
'.'],
'aspect': ['pizza place'],
'position': [[17, 18]],
'sentiment': ['Positive'],
'probs': [[0.00021825137082487345,
0.00022140667715575546,
0.9995602965354919]],
'confidence': [0.9995602965354919]},
{'sentence': "the only problem is you really have to warm up the pizza before it ' s edible , even when you order ahead .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'only',
'problem',
'is',
'you',
'really',
'have',
'to',
'warm',
'up',
'the',
'pizza',
'before',
'it',
"'",
's',
'edible',
',',
'even',
'when',
'you',
'order',
'ahead',
'.'],
'aspect': ['pizza'],
'position': [[11]],
'sentiment': ['Negative'],
'probs': [[0.9986129999160767,
0.0009791902266442776,
0.0004078947240486741]],
'confidence': [0.9986129999160767]},
{'sentence': 'best sushi in town .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['best', 'sushi', 'in', 'town', '.'],
'aspect': ['sushi'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00021649357222486287,
0.0002817070053424686,
0.9995018243789673]],
'confidence': [0.9995018243789673]},
{'sentence': 'the best calamari in seattle !',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the', 'best', 'calamari', 'in', 'seattle', '!'],
'aspect': ['calamari'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.000208173762075603,
0.00028659976669587195,
0.9995052814483643]],
'confidence': [0.9995052814483643]},
{'sentence': ' – . . . and the best summertime deck experience - - they will even bring you a blanket if you get cold in the seattle evening weather .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'.',
'.',
'.',
'and',
'the',
'best',
'summertime',
'deck',
'experience',
'-',
'-',
'they',
'will',
'even',
'bring',
'you',
'a',
'blanket',
'if',
'you',
'get',
'cold',
'in',
'the',
'seattle',
'evening',
'weather',
'.'],
'aspect': ['best summertime'],
'position': [[7, 8, 29]],
'sentiment': ['Positive'],
'probs': [[0.0003267735883127898,
0.0002496920933481306,
0.9994235038757324]],
'confidence': [0.9994235038757324]},
{'sentence': 'a perfect place to take out of town guests any time of the year .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['a',
'perfect',
'place',
'to',
'take',
'out',
'of',
'town',
'guests',
'any',
'time',
'of',
'the',
'year',
'.'],
'aspect': ['place'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00018797129450831562,
0.0004313229292165488,
0.9993807077407837]],
'confidence': [0.9993807077407837]},
{'sentence': 'endless fun , awesome music , great staff ! ! !',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['endless',
'fun',
',',
'awesome',
'music',
',',
'great',
'staff',
'!',
'!',
'!'],
'aspect': ['music', 'staff'],
'position': [[4, 7], [4, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00026495358906686306,
0.0002428938023513183,
0.9994920492172241],
[0.0003597571048885584, 0.00022326016915030777, 0.9994169473648071]],
'confidence': [0.9994920492172241, 0.9994169473648071]},
{'sentence': ' – by far the best bar in the east village . . .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'by',
'far',
'the',
'best',
'bar',
'in',
'the',
'east',
'village',
'.',
'.',
'.'],
'aspect': ['best'],
'position': [[5, 13]],
'sentiment': ['Positive'],
'probs': [[0.00023405578394886106,
0.0002866415015887469,
0.999479353427887]],
'confidence': [0.999479353427887]},
{'sentence': 'every time " 0 - sixtynine " is called the bartender buys everyone drinks !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['every',
'time',
'"',
'0',
'-',
'sixtynine',
'"',
'is',
'called',
'the',
'bartender',
'buys',
'everyone',
'drinks',
'!'],
'aspect': ['bartender', 'drinks'],
'position': [[10, 13], [10, 13]],
'sentiment': ['Neutral', 'Neutral'],
'probs': [[0.06385757774114609, 0.9255101084709167, 0.01063235942274332],
[0.0007149748271331191, 0.9983686804771423, 0.0009164197253994644]],
'confidence': [0.9255101084709167, 0.9983686804771423]},
{'sentence': 'great draft and bottle selection and the pizza rocks .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['great',
'draft',
'and',
'bottle',
'selection',
'and',
'the',
'pizza',
'rocks',
'.'],
'aspect': ['pizza'],
'position': [[7]],
'sentiment': ['Positive'],
'probs': [[0.0001517373020760715, 0.000667092390358448, 0.9991810917854309]],
'confidence': [0.9991810917854309]},
{'sentence': "definitely has one of the best jukebox ' s i ' ve seen in a long long time .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['definitely',
'has',
'one',
'of',
'the',
'best',
'jukebox',
"'",
's',
'i',
"'",
've',
'seen',
'in',
'a',
'long',
'long',
'time',
'.'],
'aspect': ['jukebox', 'time'],
'position': [[6, 17], [6, 17]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0008823584648780525, 0.000214267463888973, 0.9989033937454224],
[0.03993585333228111, 0.9596619009971619, 0.0004022698849439621]],
'confidence': [0.9989033937454224, 0.9596619009971619]},
{'sentence': 'the food is great , the bartenders go that extra mile .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'food',
'is',
'great',
',',
'the',
'bartenders',
'go',
'that',
'extra',
'mile',
'.'],
'aspect': ['food', 'bartenders'],
'position': [[1, 6], [1, 6]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00017321138875558972,
0.0005116224056109786,
0.9993151426315308],
[0.009704084135591984, 0.00034676509676501155, 0.9899492263793945]],
'confidence': [0.9993151426315308, 0.9899492263793945]},
{'sentence': 'the owners are great fun and the beer selection is worth staying for .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'owners',
'are',
'great',
'fun',
'and',
'the',
'beer',
'selection',
'is',
'worth',
'staying',
'for',
'.'],
'aspect': ['owners', 'beer selection'],
'position': [[1, 7, 8], [1, 7, 8]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00030960841104388237,
0.00032541726250201464,
0.9993649125099182],
[0.00016264745499938726, 0.00037014810368418694, 0.9994671940803528]],
'confidence': [0.9993649125099182, 0.9994671940803528]},
{'sentence': 'and the upstairs is a great place to hang out .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['and',
'the',
'upstairs',
'is',
'a',
'great',
'place',
'to',
'hang',
'out',
'.'],
'aspect': ['upstairs'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.0001999004016397521,
0.0015187005046755075,
0.9982813596725464]],
'confidence': [0.9982813596725464]},
{'sentence': 'not alot of smoking places left in new york , but i have found my favorite smoking balconey in the city .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['not',
'alot',
'of',
'smoking',
'places',
'left',
'in',
'new',
'york',
',',
'but',
'i',
'have',
'found',
'my',
'favorite',
'smoking',
'balconey',
'in',
'the',
'city',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'the sushi here is delicious !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'sushi', 'here', 'is', 'delicious', '!'],
'aspect': ['sushi'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00013973464956507087,
0.000578561273869127,
0.9992817044258118]],
'confidence': [0.9992817044258118]},
{'sentence': 'they have a wide variety of fish and they even list which oceans they come from ; atlantic or pacific .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['they',
'have',
'a',
'wide',
'variety',
'of',
'fish',
'and',
'they',
'even',
'list',
'which',
'oceans',
'they',
'come',
'from',
';',
'atlantic',
'or',
'pacific',
'.'],
'aspect': ['variety of fish'],
'position': [[4, 5, 6]],
'sentiment': ['Positive'],
'probs': [[0.00015836114471312612, 0.00032992803608067334, 0.99951171875]],
'confidence': [0.99951171875]},
{'sentence': "i ' ve had the jellyfish , horse mackerel , blue fin tuna and the sake ikura roll among others , and they were all good .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
"'",
've',
'had',
'the',
'jellyfish',
',',
'horse',
'mackerel',
',',
'blue',
'fin',
'tuna',
'and',
'the',
'sake',
'ikura',
'roll',
'among',
'others',
',',
'and',
'they',
'were',
'all',
'good',
'.'],
'aspect': ['jellyfish',
'horse mackerel',
'blue fin tuna',
'sake ikura roll'],
'position': [[5, 7, 8, 10, 11, 12, 15, 16, 17],
[5, 7, 8, 10, 11, 12, 15, 16, 17],
[5, 7, 8, 10, 11, 12, 15, 16, 17],
[5, 7, 8, 10, 11, 12, 15, 16, 17]],
'sentiment': ['Neutral', 'Positive', 'Positive', 'Positive'],
'probs': [[0.0004492442531045526, 0.6333025693893433, 0.36624816060066223],
[0.0004150650347582996, 0.4647831916809082, 0.5348017811775208],
[0.00032221744186244905, 0.18077251315116882, 0.818905234336853],
[0.00014641074812971056, 0.001111288322135806, 0.9987422823905945]],
'confidence': [0.6333025693893433,
0.5348017811775208,
0.818905234336853,
0.9987422823905945]},
{'sentence': 'my only negative comment is that i wish the pieces were a little bigger .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['my',
'only',
'negative',
'comment',
'is',
'that',
'i',
'wish',
'the',
'pieces',
'were',
'a',
'little',
'bigger',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'the decor is rustic , traditional japanese .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['the',
'decor',
'is',
'rustic',
',',
'traditional',
'japanese',
'.'],
'aspect': ['decor', 'japanese'],
'position': [[1, 6], [1, 6]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0004668357432819903, 0.29282766580581665, 0.7067055702209473],
[0.00015294742479454726, 0.001143882516771555, 0.998703122138977]],
'confidence': [0.7067055702209473, 0.998703122138977]},
{'sentence': 'the crowd is mixed yuppies , young and old .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'crowd',
'is',
'mixed',
'yuppies',
',',
'young',
'and',
'old',
'.'],
'aspect': ['crowd'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.8289292454719543, 0.17047710716724396, 0.0005937205860391259]],
'confidence': [0.8289292454719543]},
{'sentence': 'the service was courteous and attentive .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'service', 'was', 'courteous', 'and', 'attentive', '.'],
'aspect': ['service'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0002197568683186546,
0.00024636703892610967,
0.9995338916778564]],
'confidence': [0.9995338916778564]},
{'sentence': 'mediocre food',
'IOB': ['O', 'B-ASP'],
'tokens': ['mediocre', 'food'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.7428838014602661, 0.23778919875621796, 0.01932707615196705]],
'confidence': [0.7428838014602661]},
{'sentence': 'the outside patio area has an abbreviated menu .',
'IOB': ['O', 'B-ASP', 'I-ASP', 'I-ASP', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['the',
'outside',
'patio',
'area',
'has',
'an',
'abbreviated',
'menu',
'.'],
'aspect': ['outside patio area', 'menu'],
'position': [[1, 2, 3, 7], [1, 2, 3, 7]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.0010740694124251604, 0.998214602470398, 0.00071131088770926],
[0.692884087562561, 0.29055023193359375, 0.016565678641200066]],
'confidence': [0.998214602470398, 0.692884087562561]},
{'sentence': 'my g / f and i both agreed the food was very mediocre especially considering the price .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['my',
'g',
'/',
'f',
'and',
'i',
'both',
'agreed',
'the',
'food',
'was',
'very',
'mediocre',
'especially',
'considering',
'the',
'price',
'.'],
'aspect': ['food', 'price'],
'position': [[9, 16], [9, 16]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9981821775436401,
0.0015338993398472667,
0.00028387331985868514],
[0.008981307968497276, 0.9906663298606873, 0.00035228877095505595]],
'confidence': [0.9981821775436401, 0.9906663298606873]},
{'sentence': 'we are locals , and get the feeling the only way this place survives with such average food is because most customers are probably one - time customer tourists .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['we',
'are',
'locals',
',',
'and',
'get',
'the',
'feeling',
'the',
'only',
'way',
'this',
'place',
'survives',
'with',
'such',
'average',
'food',
'is',
'because',
'most',
'customers',
'are',
'probably',
'one',
'-',
'time',
'customer',
'tourists',
'.'],
'aspect': ['food'],
'position': [[17]],
'sentiment': ['Neutral'],
'probs': [[0.43249598145484924, 0.5666136741638184, 0.0008902712143026292]],
'confidence': [0.5666136741638184]},
{'sentence': 'service was decent .',
'IOB': ['B-ASP', 'O', 'O', 'O'],
'tokens': ['service', 'was', 'decent', '.'],
'aspect': ['service'],
'position': [[0]],
'sentiment': ['Neutral'],
'probs': [[0.0025963594671338797, 0.7756637334823608, 0.22173985838890076]],
'confidence': [0.7756637334823608]},
{'sentence': 'drinks were good .',
'IOB': ['B-ASP', 'O', 'O', 'O'],
'tokens': ['drinks', 'were', 'good', '.'],
'aspect': ['drinks'],
'position': [[0]],
'sentiment': ['Positive'],
'probs': [[0.00020440711523406208, 0.00216952757909894, 0.997626006603241]],
'confidence': [0.997626006603241]},
{'sentence': "unless you are just stopping in for a few drinks i would n ' t recommend going here .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['unless',
'you',
'are',
'just',
'stopping',
'in',
'for',
'a',
'few',
'drinks',
'i',
'would',
'n',
"'",
't',
'recommend',
'going',
'here',
'.'],
'aspect': ['drinks'],
'position': [[9]],
'sentiment': ['Negative'],
'probs': [[0.8302331566810608, 0.16928333044052124, 0.00048343525850214064]],
'confidence': [0.8302331566810608]},
{'sentence': 'excellent food , nice ambience , fairly expensive',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['excellent',
'food',
',',
'nice',
'ambience',
',',
'fairly',
'expensive'],
'aspect': ['food', 'ambience'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0007893432048149407, 0.00022995461768005043, 0.998980700969696],
[0.0003892819513566792, 0.0003007578488904983, 0.9993098974227905]],
'confidence': [0.998980700969696, 0.9993098974227905]},
{'sentence': ' – i loved the pumpkin ravioli and the goat cheese gnocchi ( 5 big ones to a plate instead of 20 or so little gnocchis ) and my sister loved her filet mignon on top of spinach and mashed potatoes .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'loved',
'the',
'pumpkin',
'ravioli',
'and',
'the',
'goat',
'cheese',
'gnocchi',
'(',
'5',
'big',
'ones',
'to',
'a',
'plate',
'instead',
'of',
'20',
'or',
'so',
'little',
'gnocchis',
')',
'and',
'my',
'sister',
'loved',
'her',
'filet',
'mignon',
'on',
'top',
'of',
'spinach',
'and',
'mashed',
'potatoes',
'.'],
'aspect': ['the pumpkin',
'the goat cheese',
'a',
'her filet',
'on top of',
'and mashed'],
'position': [[4, 5, 8, 9, 10, 17, 31, 32, 34, 35, 36, 38, 39, 41],
[4, 5, 8, 9, 10, 17, 31, 32, 34, 35, 36, 38, 39, 41],
[4, 5, 8, 9, 10, 17, 31, 32, 34, 35, 36, 38, 39, 41],
[4, 5, 8, 9, 10, 17, 31, 32, 34, 35, 36, 38, 39, 41],
[4, 5, 8, 9, 10, 17, 31, 32, 34, 35, 36, 38, 39, 41],
[4, 5, 8, 9, 10, 17, 31, 32, 34, 35, 36, 38, 39, 41]],
'sentiment': ['Positive',
'Positive',
'Positive',
'Positive',
'Positive',
'Neutral'],
'probs': [[0.005655864719301462, 0.0005297308671288192, 0.9938144683837891],
[0.003062111558392644, 0.0014529466861858964, 0.9954850673675537],
[0.0044624838046729565, 0.001086746109649539, 0.9944508075714111],
[0.0010635927319526672, 0.0007335287518799305, 0.998202919960022],
[0.0010276933899149299, 0.41486504673957825, 0.5841072797775269],
[0.00039018556708469987, 0.9937542080879211, 0.005855616647750139]],
'confidence': [0.9938144683837891,
0.9954850673675537,
0.9944508075714111,
0.998202919960022,
0.5841072797775269,
0.9937542080879211]},
{'sentence': 'the ambiance was a peaceful and relaxing break amongst all the kids running around in downtown disney .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'ambiance',
'was',
'a',
'peaceful',
'and',
'relaxing',
'break',
'amongst',
'all',
'the',
'kids',
'running',
'around',
'in',
'downtown',
'disney',
'.'],
'aspect': ['ambiance', 'disney'],
'position': [[1, 16], [1, 16]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0011881296522915363,
0.00017089693574234843,
0.9986409544944763],
[0.0003159630869049579, 0.9993114471435547, 0.00037258901284076273]],
'confidence': [0.9986409544944763, 0.9993114471435547]},
{'sentence': 'it was romantic - and even nice even with my sister , reminded me of italy , and had artwork and music that kept up the feeling of being in a mediterrean villa .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['it',
'was',
'romantic',
'-',
'and',
'even',
'nice',
'even',
'with',
'my',
'sister',
',',
'reminded',
'me',
'of',
'italy',
',',
'and',
'had',
'artwork',
'and',
'music',
'that',
'kept',
'up',
'the',
'feeling',
'of',
'being',
'in',
'a',
'mediterrean',
'villa',
'.'],
'aspect': ['artwork', 'music'],
'position': [[19, 21], [19, 21]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00021228846162557602,
0.00038368941750377417,
0.9994039535522461],
[0.00020407912961672992, 0.0004224635486025363, 0.9993734955787659]],
'confidence': [0.9994039535522461, 0.9993734955787659]},
{'sentence': 'best indian food in l . a .',
'IOB': ['O', 'B-ASP', 'I-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['best', 'indian', 'food', 'in', 'l', '.', 'a', '.'],
'aspect': ['indian food'],
'position': [[1, 2]],
'sentiment': ['Positive'],
'probs': [[0.000254050362855196,
0.00024756582570262253,
0.9994983673095703]],
'confidence': [0.9994983673095703]},
{'sentence': 'the chicken curry and chicken tikka masala are my favorite meat dishes .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O'],
'tokens': ['the',
'chicken',
'curry',
'and',
'chicken',
'tikka',
'masala',
'are',
'my',
'favorite',
'meat',
'dishes',
'.'],
'aspect': ['chicken tikka masala', 'meat dishes'],
'position': [[4, 5, 6, 10, 11], [4, 5, 6, 10, 11]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00017868398572318256, 0.0005080894334241748, 0.999313235282898],
[0.00019508873810991645, 0.000387435284210369, 0.9994175434112549]],
'confidence': [0.999313235282898, 0.9994175434112549]},
{'sentence': 'the chana masala ( garbanzo beans ) are also excellent .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'chana',
'masala',
'(',
'garbanzo',
'beans',
')',
'are',
'also',
'excellent',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': "it ' s located in a strip mall near the beverly center , not the greatest location , but the food keeps me coming back for more .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['it',
"'",
's',
'located',
'in',
'a',
'strip',
'mall',
'near',
'the',
'beverly',
'center',
',',
'not',
'the',
'greatest',
'location',
',',
'but',
'the',
'food',
'keeps',
'me',
'coming',
'back',
'for',
'more',
'.'],
'aspect': ['location', 'food'],
'position': [[16, 20], [16, 20]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.23422099649906158, 0.003018526826053858, 0.7627604007720947],
[0.0001943973620655015, 0.00034104802762158215, 0.9994645714759827]],
'confidence': [0.7627604007720947, 0.9994645714759827]},
{'sentence': 'never too crowded and always great service .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['never',
'too',
'crowded',
'and',
'always',
'great',
'service',
'.'],
'aspect': ['service'],
'position': [[6]],
'sentiment': ['Positive'],
'probs': [[0.00024127385404426605,
0.00024834086070768535,
0.9995104074478149]],
'confidence': [0.9995104074478149]},
{'sentence': 'i think i have probably tried each item on their menu at least once it is all excellent .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'think',
'i',
'have',
'probably',
'tried',
'each',
'item',
'on',
'their',
'menu',
'at',
'least',
'once',
'it',
'is',
'all',
'excellent',
'.'],
'aspect': ['menu'],
'position': [[10]],
'sentiment': ['Positive'],
'probs': [[0.001384215196594596, 0.13670693337917328, 0.8619088530540466]],
'confidence': [0.8619088530540466]},
{'sentence': 'i can highly recommend their various saag and paneer and korma .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'B-ASP', 'O'],
'tokens': ['i',
'can',
'highly',
'recommend',
'their',
'various',
'saag',
'and',
'paneer',
'and',
'korma',
'.'],
'aspect': ['paneer', 'korma'],
'position': [[8, 10], [8, 10]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00017502627451904118,
0.0004120980156585574,
0.9994128942489624],
[0.00021475671383086592, 0.0002723881625570357, 0.9995129108428955]],
'confidence': [0.9994128942489624, 0.9995129108428955]},
{'sentence': 'i appreciate their delivery too .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['i', 'appreciate', 'their', 'delivery', 'too', '.'],
'aspect': ['delivery'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.00022073218133300543,
0.0002572502417024225,
0.9995219707489014]],
'confidence': [0.9995219707489014]},
{'sentence': 'nice food but no spice !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['nice', 'food', 'but', 'no', 'spice', '!'],
'aspect': ['food', 'spice'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.7750080227851868, 0.001080976682715118, 0.22391101717948914],
[0.9987373948097229, 0.0009680421790108085, 0.00029455305775627494]],
'confidence': [0.7750080227851868, 0.9987373948097229]},
{'sentence': ' – i really enjoyed my meal here .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', '[SEP]'],
'tokens': [' ', '–', 'i', 'really', 'enjoyed', 'my', 'meal', 'here', '.'],
'aspect': ['my'],
'position': [[5, 8]],
'sentiment': ['Positive'],
'probs': [[0.00018292138702236116,
0.00031583296367898583,
0.9995012283325195]],
'confidence': [0.9995012283325195]},
{'sentence': 'i had yummy lamb korma , saag paneer , samosas , naan , etc .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['i',
'had',
'yummy',
'lamb',
'korma',
',',
'saag',
'paneer',
',',
'samosas',
',',
'naan',
',',
'etc',
'.'],
'aspect': ['lamb korma', 'saag paneer', 'naan'],
'position': [[3, 4, 6, 7, 11], [3, 4, 6, 7, 11], [3, 4, 6, 7, 11]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00022984192764852196, 0.0005044223507866263, 0.999265730381012],
[0.00018523943435866386, 0.008469684980809689, 0.9913451671600342],
[0.00020254048286005855, 0.0007104370160959661, 0.9990869760513306]],
'confidence': [0.999265730381012, 0.9913451671600342, 0.9990869760513306]},
{'sentence': 'the food was all good but it was way too mild .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'food',
'was',
'all',
'good',
'but',
'it',
'was',
'way',
'too',
'mild',
'.'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.2687007486820221, 0.009135579690337181, 0.7221636772155762]],
'confidence': [0.7221636772155762]},
{'sentence': 'i should have thought to bring it up but never expected the food to be that mild .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'should',
'have',
'thought',
'to',
'bring',
'it',
'up',
'but',
'never',
'expected',
'the',
'food',
'to',
'be',
'that',
'mild',
'.'],
'aspect': ['food'],
'position': [[12]],
'sentiment': ['Positive'],
'probs': [[0.0007271529757417738,
0.0003870305372402072,
0.9988858103752136]],
'confidence': [0.9988858103752136]},
{'sentence': "the naan was some of the best i ' ve had and i really enjoyed the bhartha , not too tomatoey .",
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'naan',
'was',
'some',
'of',
'the',
'best',
'i',
"'",
've',
'had',
'and',
'i',
'really',
'enjoyed',
'the',
'bhartha',
',',
'not',
'too',
'tomatoey',
'.'],
'aspect': ['naan', 'bhartha'],
'position': [[1, 16], [1, 16]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00030118116410449147,
0.0003500392776913941,
0.9993488192558289],
[0.0005770806455984712, 0.00042072971700690687, 0.9990021586418152]],
'confidence': [0.9993488192558289, 0.9990021586418152]},
{'sentence': 'even the chickpeas , which i normally find too dry , were good .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['even',
'the',
'chickpeas',
',',
'which',
'i',
'normally',
'find',
'too',
'dry',
',',
'were',
'good',
'.'],
'aspect': ['chickpeas'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.09685725718736649, 0.00030885852174833417, 0.902833878993988]],
'confidence': [0.902833878993988]},
{'sentence': " – i do n ' t understand how i was a stranger to this place for so long . . . the fajita salad , the colorado , the fajitas - everything is delicious .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'do',
'n',
"'",
't',
'understand',
'how',
'i',
'was',
'a',
'stranger',
'to',
'this',
'place',
'for',
'so',
'long',
'.',
'.',
'.',
'the',
'fajita',
'salad',
',',
'the',
'colorado',
',',
'the',
'fajitas',
'-',
'everything',
'is',
'delicious',
'.'],
'aspect': ['the fajita', 'the'],
'position': [[22, 23, 29, 35], [22, 23, 29, 35]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002673438866622746, 0.0007156056817620993, 0.9990170001983643],
[0.00020126505114603788, 0.005672076251357794, 0.9941266775131226]],
'confidence': [0.9990170001983643, 0.9941266775131226]},
{'sentence': 'i love the warm & cosy environment .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['i', 'love', 'the', 'warm', '&', 'cosy', 'environment', '.'],
'aspect': ['environment'],
'position': [[6]],
'sentiment': ['Positive'],
'probs': [[0.00015679537318646908,
0.00037653918843716383,
0.9994667172431946]],
'confidence': [0.9994667172431946]},
{'sentence': "i just found out that you can have the place to yourself on nights and weekends for a private party - ca n ' t wait to celebrate my next birthday there .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'just',
'found',
'out',
'that',
'you',
'can',
'have',
'the',
'place',
'to',
'yourself',
'on',
'nights',
'and',
'weekends',
'for',
'a',
'private',
'party',
'-',
'ca',
'n',
"'",
't',
'wait',
'to',
'celebrate',
'my',
'next',
'birthday',
'there',
'.'],
'aspect': ['place'],
'position': [[9]],
'sentiment': ['Positive'],
'probs': [[0.00033231923589482903,
0.0002891582262236625,
0.9993785619735718]],
'confidence': [0.9993785619735718]},
{'sentence': 'best restaurant in the world , great decor , great customer service , friendly manager',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP'],
'tokens': ['best',
'restaurant',
'in',
'the',
'world',
',',
'great',
'decor',
',',
'great',
'customer',
'service',
',',
'friendly',
'manager'],
'aspect': ['decor', 'service', 'manager'],
'position': [[7, 11, 14], [7, 11, 14], [7, 11, 14]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.0002370562287978828, 0.0002323866938240826, 0.999530553817749],
[0.0002444363199174404, 0.0002426368009764701, 0.9995130300521851],
[0.00025916448794305325, 0.0002544335729908198, 0.9994864463806152]],
'confidence': [0.999530553817749, 0.9995130300521851, 0.9994864463806152]},
{'sentence': 'i am never disappointed with there food .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['i', 'am', 'never', 'disappointed', 'with', 'there', 'food', '.'],
'aspect': ['food'],
'position': [[6]],
'sentiment': ['Positive'],
'probs': [[0.0001581139222253114,
0.00035806340747512877,
0.9994838237762451]],
'confidence': [0.9994838237762451]},
{'sentence': 'the atmosphere is great .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the', 'atmosphere', 'is', 'great', '.'],
'aspect': ['atmosphere'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00016840841271914542,
0.0003351664636284113,
0.9994964599609375]],
'confidence': [0.9994964599609375]},
{'sentence': 'great lunch spot',
'IOB': ['O', 'B-ASP', 'I-ASP'],
'tokens': ['great', 'lunch', 'spot'],
'aspect': ['lunch spot'],
'position': [[1, 2]],
'sentiment': ['Positive'],
'probs': [[0.0002897465310525149,
0.0002103615115629509,
0.9994997978210449]],
'confidence': [0.9994997978210449]},
{'sentence': ' – great financial district mexican spot .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', '[SEP]'],
'tokens': [' ',
'–',
'great',
'financial',
'district',
'mexican',
'spot',
'.'],
'aspect': ['mexican'],
'position': [[5, 7]],
'sentiment': ['Positive'],
'probs': [[0.0001725806505419314,
0.0003839033597614616,
0.9994434714317322]],
'confidence': [0.9994434714317322]},
{'sentence': 'always busy , but they are good at seating you promptly and have quick service .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['always',
'busy',
',',
'but',
'they',
'are',
'good',
'at',
'seating',
'you',
'promptly',
'and',
'have',
'quick',
'service',
'.'],
'aspect': ['seating', 'service'],
'position': [[8, 14], [8, 14]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00012193328439025208,
0.0006970855756662786,
0.9991809725761414],
[0.00018654795712791383, 0.00027835354558192194, 0.999535083770752]],
'confidence': [0.9991809725761414, 0.999535083770752]},
{'sentence': "everything i ' ve had here is good , taco salads , burritos , enchiladas i love this place .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['everything',
'i',
"'",
've',
'had',
'here',
'is',
'good',
',',
'taco',
'salads',
',',
'burritos',
',',
'enchiladas',
'i',
'love',
'this',
'place',
'.'],
'aspect': ['taco salads', 'burritos', 'enchiladas'],
'position': [[9, 10, 12, 14], [9, 10, 12, 14], [9, 10, 12, 14]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00015326423454098403, 0.000656032410915941, 0.999190628528595],
[0.00024367726291529834, 0.0007266697939485312, 0.9990296363830566],
[0.000286780676105991, 0.0004979614750482142, 0.9992152452468872]],
'confidence': [0.999190628528595, 0.9990296363830566, 0.9992152452468872]},
{'sentence': 'also have great margaritas !',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['also', 'have', 'great', 'margaritas', '!'],
'aspect': ['margaritas'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.00026401830837130547,
0.00033920479472726583,
0.999396800994873]],
'confidence': [0.999396800994873]},
{'sentence': 'lebanese food ! yum !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['lebanese', 'food', '!', 'yum', '!'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00017176178516820073,
0.0007766110356897116,
0.9990516304969788]],
'confidence': [0.9990516304969788]},
{'sentence': " – i ' ve been to open sesame only once , but i ' m still reeling from the experience ! !",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
"'",
've',
'been',
'to',
'open',
'sesame',
'only',
'once',
',',
'but',
'i',
"'",
'm',
'still',
'reeling',
'from',
'the',
'experience',
'!',
'!'],
'aspect': ['to open'],
'position': [[6, 7, 22]],
'sentiment': ['Neutral'],
'probs': [[0.20641522109508514, 0.5608765482902527, 0.23270824551582336]],
'confidence': [0.5608765482902527]},
{'sentence': 'the food is simply unforgettable !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'food', 'is', 'simply', 'unforgettable', '!'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00022640109818894416,
0.0002450462488923222,
0.9995285272598267]],
'confidence': [0.9995285272598267]},
{'sentence': 'the presentation of the food was an added bonus , it looked just as great as it tasted !',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'presentation',
'of',
'the',
'food',
'was',
'an',
'added',
'bonus',
',',
'it',
'looked',
'just',
'as',
'great',
'as',
'it',
'tasted',
'!'],
'aspect': ['food', 'looked'],
'position': [[4, 11], [4, 11]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0001418222818756476, 0.003407760988920927, 0.9964504241943359],
[0.00015668905689381063, 0.0008303752983920276, 0.99901282787323]],
'confidence': [0.9964504241943359, 0.99901282787323]},
{'sentence': 'my best friend had the chicken shawarma and she still raves about it being the best anywhere !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['my',
'best',
'friend',
'had',
'the',
'chicken',
'shawarma',
'and',
'she',
'still',
'raves',
'about',
'it',
'being',
'the',
'best',
'anywhere',
'!'],
'aspect': ['chicken shawarma'],
'position': [[5, 6]],
'sentiment': ['Positive'],
'probs': [[0.0001179342289105989,
0.0029529931489378214,
0.9969291090965271]],
'confidence': [0.9969291090965271]},
{'sentence': 'the staff are friendly and the decor was ethic and colorful .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'staff',
'are',
'friendly',
'and',
'the',
'decor',
'was',
'ethic',
'and',
'colorful',
'.'],
'aspect': ['staff', 'decor'],
'position': [[1, 6], [1, 6]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0004097851342521608, 0.00023742603661958128, 0.999352753162384],
[0.00013907102402299643, 0.0004170110041741282, 0.9994439482688904]],
'confidence': [0.999352753162384, 0.9994439482688904]},
{'sentence': 'go to open sesame ! ! !',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['go', 'to', 'open', 'sesame', '!', '!', '!'],
'aspect': ['sesame'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.00048471023910678923, 0.13232658803462982, 0.8671886324882507]],
'confidence': [0.8671886324882507]},
{'sentence': 'holy hummus !',
'IOB': ['O', 'B-ASP', 'O'],
'tokens': ['holy', 'hummus', '!'],
'aspect': ['hummus'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00044959032675251365,
0.0002439626696286723,
0.9993064403533936]],
'confidence': [0.9993064403533936]},
{'sentence': ' – the food is here is incredible , though the quality is inconsistent during lunch .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'the',
'food',
'is',
'here',
'is',
'incredible',
',',
'though',
'the',
'quality',
'is',
'inconsistent',
'during',
'lunch',
'.'],
'aspect': ['the', 'the', 'during'],
'position': [[2, 10, 14, 16], [2, 10, 14, 16], [2, 10, 14, 16]],
'sentiment': ['Positive', 'Positive', 'Neutral'],
'probs': [[0.0016130313742905855,
0.00023668778885621578,
0.9981503486633301],
[0.0016130313742905855, 0.00023668778885621578, 0.9981503486633301],
[0.021464360877871513, 0.9781894087791443, 0.0003462487948127091]],
'confidence': [0.9981503486633301, 0.9981503486633301, 0.9781894087791443]},
{'sentence': 'dinners have always been excellent , in terms of food quality .',
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O'],
'tokens': ['dinners',
'have',
'always',
'been',
'excellent',
',',
'in',
'terms',
'of',
'food',
'quality',
'.'],
'aspect': ['dinners', 'food quality'],
'position': [[0, 9, 10], [0, 9, 10]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00030317160417325795, 0.15269286930561066, 0.8470038771629333],
[0.00018999593157786876, 0.0002693010901566595, 0.9995406866073608]],
'confidence': [0.8470038771629333, 0.9995406866073608]},
{'sentence': 'the open sesame combo plate is a bargain for the heap of food given .',
'IOB': ['O',
'B-ASP',
'I-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O'],
'tokens': ['the',
'open',
'sesame',
'combo',
'plate',
'is',
'a',
'bargain',
'for',
'the',
'heap',
'of',
'food',
'given',
'.'],
'aspect': ['open sesame combo plate', 'food'],
'position': [[1, 2, 3, 4, 12], [1, 2, 3, 4, 12]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00043075656867586076, 0.9086601734161377, 0.09090909361839294],
[0.00031374613172374666, 0.00033773441100493073, 0.9993484616279602]],
'confidence': [0.9086601734161377, 0.9993484616279602]},
{'sentence': 'the side of potatoes is to die for , as is the labne ( yogurt dip ) .',
'IOB': ['O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'I-ASP',
'O',
'O'],
'tokens': ['the',
'side',
'of',
'potatoes',
'is',
'to',
'die',
'for',
',',
'as',
'is',
'the',
'labne',
'(',
'yogurt',
'dip',
')',
'.'],
'aspect': ['of potatoes', 'labne ( yogurt dip'],
'position': [[2, 3, 12, 13, 14, 15], [2, 3, 12, 13, 14, 15]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0013295637909322977,
0.00021241525246296078,
0.9984580278396606],
[0.0002246363292215392, 0.9975995421409607, 0.0021758258808404207]],
'confidence': [0.9984580278396606, 0.9975995421409607]},
{'sentence': 'also , they serve the best hummus in america , with a drizzle of fragrant olive oil ( which , i believe is the traditional way ) !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['also',
',',
'they',
'serve',
'the',
'best',
'hummus',
'in',
'america',
',',
'with',
'a',
'drizzle',
'of',
'fragrant',
'olive',
'oil',
'(',
'which',
',',
'i',
'believe',
'is',
'the',
'traditional',
'way',
')',
'!'],
'aspect': ['hummus', 'olive oil'],
'position': [[6, 15, 16], [6, 15, 16]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.00019371288362890482, 0.002861138666048646, 0.9969450831413269],
[0.00030079929274506867, 0.9849721789360046, 0.014726991765201092]],
'confidence': [0.9969450831413269, 0.9849721789360046]},
{'sentence': 'the only drawback is the crowded seating and the slow service .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['the',
'only',
'drawback',
'is',
'the',
'crowded',
'seating',
'and',
'the',
'slow',
'service',
'.'],
'aspect': ['seating', 'service'],
'position': [[6, 10], [6, 10]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9983285069465637,
0.0014701631153002381,
0.00020134579972364008],
[0.9989609718322754, 0.0008205282501876354, 0.00021852296777069569]],
'confidence': [0.9983285069465637, 0.9989609718322754]},
{'sentence': "however , this place is a gem , and i wo n ' t stop going back .",
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['however',
',',
'this',
'place',
'is',
'a',
'gem',
',',
'and',
'i',
'wo',
'n',
"'",
't',
'stop',
'going',
'back',
'.'],
'aspect': ['place'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.0002962636644951999,
0.00026798801263794303,
0.9994357228279114]],
'confidence': [0.9994357228279114]},
{'sentence': 'great beer',
'IOB': ['O', 'B-ASP'],
'tokens': ['great', 'beer'],
'aspect': ['beer'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0003887037164531648,
0.00023336919548455626,
0.9993778467178345]],
'confidence': [0.9993778467178345]},
{'sentence': ' – my first time to dine at this restaurant was with my son and it was absolutely horrible !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'my',
'first',
'time',
'to',
'dine',
'at',
'this',
'restaurant',
'was',
'with',
'my',
'son',
'and',
'it',
'was',
'absolutely',
'horrible',
'!'],
'aspect': ['to'],
'position': [[5, 19]],
'sentiment': ['Negative'],
'probs': [[0.9985804557800293,
0.0011595202377066016,
0.00026000395882874727]],
'confidence': [0.9985804557800293]},
{'sentence': 'i swore never to return for a warm beer and mediocre meal .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['i',
'swore',
'never',
'to',
'return',
'for',
'a',
'warm',
'beer',
'and',
'mediocre',
'meal',
'.'],
'aspect': ['beer', 'meal'],
'position': [[8, 11], [8, 11]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.0008388262358494103, 0.8072358965873718, 0.1919253170490265],
[0.9987406134605408, 0.0009270944865420461, 0.00033232380519621074]],
'confidence': [0.8072358965873718, 0.9987406134605408]},
{'sentence': 'the band was very good and the service was attentive .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the',
'band',
'was',
'very',
'good',
'and',
'the',
'service',
'was',
'attentive',
'.'],
'aspect': ['band', 'service'],
'position': [[1, 7], [1, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002871451433748007,
0.00023951707407832146,
0.9994733929634094],
[0.00021985253260936588, 0.0002925799635704607, 0.9994875192642212]],
'confidence': [0.9994733929634094, 0.9994875192642212]},
{'sentence': 'we ordered a selection of the small plates , and the shoe string onions , goat cheese pizza , grilled asparagus and fried brie with fruit were all very good .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['we',
'ordered',
'a',
'selection',
'of',
'the',
'small',
'plates',
',',
'and',
'the',
'shoe',
'string',
'onions',
',',
'goat',
'cheese',
'pizza',
',',
'grilled',
'asparagus',
'and',
'fried',
'brie',
'with',
'fruit',
'were',
'all',
'very',
'good',
'.'],
'aspect': ['plates', 'goat cheese pizza', 'grilled asparagus', 'brie'],
'position': [[7, 15, 16, 17, 19, 20, 23],
[7, 15, 16, 17, 19, 20, 23],
[7, 15, 16, 17, 19, 20, 23],
[7, 15, 16, 17, 19, 20, 23]],
'sentiment': ['Neutral', 'Positive', 'Positive', 'Positive'],
'probs': [[0.002361456397920847, 0.996452808380127, 0.0011857122881338],
[0.00322073046118021, 0.06874430924654007, 0.9280349612236023],
[0.0024973510298877954, 0.008882124908268452, 0.9886205792427063],
[0.001364019582979381, 0.07234998047351837, 0.926285982131958]],
'confidence': [0.996452808380127,
0.9280349612236023,
0.9886205792427063,
0.926285982131958]},
{'sentence': 'we have since returned and also had a great experience , sampling more small plates and a variety of the beer ( cold and good ) .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['we',
'have',
'since',
'returned',
'and',
'also',
'had',
'a',
'great',
'experience',
',',
'sampling',
'more',
'small',
'plates',
'and',
'a',
'variety',
'of',
'the',
'beer',
'(',
'cold',
'and',
'good',
')',
'.'],
'aspect': ['plates', 'beer'],
'position': [[14, 20], [14, 20]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00019120344950351864,
0.9978274703025818,
0.0019812919199466705],
[0.00019692302157636732, 0.00034261448308825493, 0.9994603991508484]],
'confidence': [0.9978274703025818, 0.9994603991508484]},
{'sentence': 'we did have the same waiter the second time , so maybe the service is spotty and our luck is good .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['we',
'did',
'have',
'the',
'same',
'waiter',
'the',
'second',
'time',
',',
'so',
'maybe',
'the',
'service',
'is',
'spotty',
'and',
'our',
'luck',
'is',
'good',
'.'],
'aspect': ['waiter', 'service'],
'position': [[5, 13], [5, 13]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.5510749220848083, 0.4276126027107239, 0.021312475204467773],
[0.36400797963142395, 0.6340768337249756, 0.0019152254099026322]],
'confidence': [0.5510749220848083, 0.6340768337249756]},
{'sentence': 'sunday afternoons there is a band playing and it is lots of fun .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['sunday',
'afternoons',
'there',
'is',
'a',
'band',
'playing',
'and',
'it',
'is',
'lots',
'of',
'fun',
'.'],
'aspect': ['band'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.0001255582319572568,
0.0021231116261333227,
0.9977512955665588]],
'confidence': [0.9977512955665588]},
{'sentence': "seattle ' s best winelist",
'IOB': ['O', 'O', 'O', 'O', 'B-ASP'],
'tokens': ['seattle', "'", 's', 'best', 'winelist'],
'aspect': ['winelist'],
'position': [[4]],
'sentiment': ['Positive'],
'probs': [[0.0001922933734022081,
0.0002561691217124462,
0.9995514750480652]],
'confidence': [0.9995514750480652]},
{'sentence': " – ray ' s ( suprisingly ) has the city ' s best & most diverse wine list .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'ray',
"'",
's',
'(',
'suprisingly',
')',
'has',
'the',
'city',
"'",
's',
'best',
'&',
'most',
'diverse',
'wine',
'list',
'.'],
'aspect': ['diverse wine'],
'position': [[16, 17, 19]],
'sentiment': ['Positive'],
'probs': [[0.00017074782226700336,
0.0002547487965784967,
0.9995744824409485]],
'confidence': [0.9995744824409485]},
{'sentence': 'the sommelier is fantastic , down - to - earth , & extremely knowlegable .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'sommelier',
'is',
'fantastic',
',',
'down',
'-',
'to',
'-',
'earth',
',',
'&',
'extremely',
'knowlegable',
'.'],
'aspect': ['sommelier'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00023277186846826226,
0.0002829046861734241,
0.9994843006134033]],
'confidence': [0.9994843006134033]},
{'sentence': 'i would go back for the wine experience alone .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['i',
'would',
'go',
'back',
'for',
'the',
'wine',
'experience',
'alone',
'.'],
'aspect': ['wine'],
'position': [[6]],
'sentiment': ['Positive'],
'probs': [[0.00021760229719802737,
0.0003166206297464669,
0.9994658827781677]],
'confidence': [0.9994658827781677]},
{'sentence': 'not the place it once was',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['not', 'the', 'place', 'it', 'once', 'was'],
'aspect': ['place'],
'position': [[2]],
'sentiment': ['Negative'],
'probs': [[0.998117208480835, 0.0013505585957318544, 0.000532221223693341]],
'confidence': [0.998117208480835]},
{'sentence': ' – it is sad to see a place that was once " the " place to meet and eat for bfast or lunch , now be the place that is a big " dont bother . "',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'it',
'is',
'sad',
'to',
'see',
'a',
'place',
'that',
'was',
'once',
'"',
'the',
'"',
'place',
'to',
'meet',
'and',
'eat',
'for',
'bfast',
'or',
'lunch',
',',
'now',
'be',
'the',
'place',
'that',
'is',
'a',
'big',
'"',
'dont',
'bother',
'.',
'"'],
'aspect': ['a', 'for', 'or'],
'position': [[7, 20, 22, 37], [7, 20, 22, 37], [7, 20, 22, 37]],
'sentiment': ['Negative', 'Neutral', 'Neutral'],
'probs': [[0.9824364185333252, 0.0003632493317127228, 0.017200332134962082],
[0.001295240712352097, 0.9982988238334656, 0.0004059524508193135],
[0.0010402060579508543, 0.9985659718513489, 0.0003937967121601105]],
'confidence': [0.9824364185333252, 0.9982988238334656, 0.9985659718513489]},
{'sentence': 'the food is not what it once was ( potions have seriously seen downsizing ) prices have gone up , and the service is the worst i have experienced anywhere ( including mainland europe ) .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'food',
'is',
'not',
'what',
'it',
'once',
'was',
'(',
'potions',
'have',
'seriously',
'seen',
'downsizing',
')',
'prices',
'have',
'gone',
'up',
',',
'and',
'the',
'service',
'is',
'the',
'worst',
'i',
'have',
'experienced',
'anywhere',
'(',
'including',
'mainland',
'europe',
')',
'.'],
'aspect': ['food', 'prices', 'service'],
'position': [[1, 15, 22], [1, 15, 22], [1, 15, 22]],
'sentiment': ['Negative', 'Negative', 'Negative'],
'probs': [[0.9592967629432678, 0.0401756651699543, 0.0005274738650768995],
[0.9954214692115784, 0.004248154349625111, 0.00033033580984920263],
[0.9962913990020752, 0.0033629995305091143, 0.0003455698024481535]],
'confidence': [0.9592967629432678, 0.9954214692115784, 0.9962913990020752]},
{'sentence': 'what may be interesting to most is the worst sevice / attitude comes from the owners of this establishment .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['what',
'may',
'be',
'interesting',
'to',
'most',
'is',
'the',
'worst',
'sevice',
'/',
'attitude',
'comes',
'from',
'the',
'owners',
'of',
'this',
'establishment',
'.'],
'aspect': ['attitude', 'owners'],
'position': [[11, 15], [11, 15]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9961094260215759, 0.003628272796049714, 0.00026233773678541183],
[0.996134877204895, 0.0036835763603448868, 0.00018162418564315885]],
'confidence': [0.9961094260215759, 0.996134877204895]},
{'sentence': 'this establishment really made a marked decline after ( and this is recurring story ) the airing of food televisions " diners , drive - ins , and dives " hosted by guy fieri , in which schooner or later was subject of .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['this',
'establishment',
'really',
'made',
'a',
'marked',
'decline',
'after',
'(',
'and',
'this',
'is',
'recurring',
'story',
')',
'the',
'airing',
'of',
'food',
'televisions',
'"',
'diners',
',',
'drive',
'-',
'ins',
',',
'and',
'dives',
'"',
'hosted',
'by',
'guy',
'fieri',
',',
'in',
'which',
'schooner',
'or',
'later',
'was',
'subject',
'of',
'.'],
'aspect': ['diners', 'guy fieri'],
'position': [[21, 32, 33], [21, 32, 33]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.06382614374160767, 0.9358963370323181, 0.00027758185751736164],
[0.9963035583496094, 0.0035086222924292088, 0.00018775653734337538]],
'confidence': [0.9358963370323181, 0.9963035583496094]},
{'sentence': 'perhaps now , scooner or later falls into the " dive " category .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['perhaps',
'now',
',',
'scooner',
'or',
'later',
'falls',
'into',
'the',
'"',
'dive',
'"',
'category',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'i hope one day scooner or later returns to what it once was .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'hope',
'one',
'day',
'scooner',
'or',
'later',
'returns',
'to',
'what',
'it',
'once',
'was',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'open & cool place with the best pizza and coffee',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'B-ASP', 'O', 'B-ASP'],
'tokens': ['open',
'&',
'cool',
'place',
'with',
'the',
'best',
'pizza',
'and',
'coffee'],
'aspect': ['place', 'pizza', 'coffee'],
'position': [[3, 7, 9], [3, 7, 9], [3, 7, 9]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00017205158655997366,
0.00031146322726272047,
0.999516487121582],
[0.0001918922207551077, 0.00032111696782521904, 0.9994869232177734],
[0.00020439547370187938, 0.0003265900304540992, 0.999468982219696]],
'confidence': [0.999516487121582, 0.9994869232177734, 0.999468982219696]},
{'sentence': ' – mioposto has a very creative & delicious pizza menu .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'mioposto',
'has',
'a',
'very',
'creative',
'&',
'delicious',
'pizza',
'menu',
'.'],
'aspect': ['delicious pizza'],
'position': [[8, 9, 11]],
'sentiment': ['Positive'],
'probs': [[0.00020192438387311995,
0.00023407292610500008,
0.999563992023468]],
'confidence': [0.999563992023468]},
{'sentence': 'the coffe is very good , too .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'coffe', 'is', 'very', 'good', ',', 'too', '.'],
'aspect': ['coffe'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00016083108494058251,
0.0006780112744309008,
0.9991612434387207]],
'confidence': [0.9991612434387207]},
{'sentence': 'great open and friendly ambience .',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['great', 'open', 'and', 'friendly', 'ambience', '.'],
'aspect': ['ambience'],
'position': [[4]],
'sentiment': ['Positive'],
'probs': [[0.0001821332552935928,
0.0003087442892137915,
0.9995090961456299]],
'confidence': [0.9995090961456299]},
{'sentence': 'this place is charming and relaxing .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['this', 'place', 'is', 'charming', 'and', 'relaxing', '.'],
'aspect': ['place'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00017306403606198728,
0.0002797276829369366,
0.9995471835136414]],
'confidence': [0.9995471835136414]},
{'sentence': 'the servers behind the counter are always friendly and helpful .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'servers',
'behind',
'the',
'counter',
'are',
'always',
'friendly',
'and',
'helpful',
'.'],
'aspect': ['servers', 'counter'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0002700606419239193, 0.0007120051304809749, 0.9990178346633911],
[0.00028158220811747015, 0.9716606736183167, 0.02805769257247448]],
'confidence': [0.9990178346633911, 0.9716606736183167]},
{'sentence': "it ' s a great place to enjoy food and meet friends .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['it',
"'",
's',
'a',
'great',
'place',
'to',
'enjoy',
'food',
'and',
'meet',
'friends',
'.'],
'aspect': ['place', 'food'],
'position': [[5, 8], [5, 8]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00019096028700005263,
0.0007136529311537743,
0.9990954399108887],
[0.00015531113604083657, 0.0005087291938252747, 0.9993359446525574]],
'confidence': [0.9990954399108887, 0.9993359446525574]},
{'sentence': " – after 12 years in seattle ray ' s rates as the place we always go back to .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'after',
'12',
'years',
'in',
'seattle',
'ray',
"'",
's',
'rates',
'as',
'the',
'place',
'we',
'always',
'go',
'back',
'to',
'.'],
'aspect': ['s'],
'position': [[9, 19]],
'sentiment': ['Positive'],
'probs': [[0.0005427004070952535, 0.14826437830924988, 0.8511929512023926]],
'confidence': [0.8511929512023926]},
{'sentence': 'great food , spectacular location , and friendly service keep us coming back year after year .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['great',
'food',
',',
'spectacular',
'location',
',',
'and',
'friendly',
'service',
'keep',
'us',
'coming',
'back',
'year',
'after',
'year',
'.'],
'aspect': ['food', 'location', 'service'],
'position': [[1, 4, 8], [1, 4, 8], [1, 4, 8]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00029021239606663585,
0.0002493992797099054,
0.9994603991508484],
[0.00024153005506377667, 0.0002464389835949987, 0.9995120763778687],
[0.00020347282406874, 0.00025516172172501683, 0.9995414018630981]],
'confidence': [0.9994603991508484, 0.9995120763778687, 0.9995414018630981]},
{'sentence': 'enjoyed the food',
'IOB': ['O', 'O', 'B-ASP'],
'tokens': ['enjoyed', 'the', 'food'],
'aspect': ['food'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00021523154282476753,
0.00029207547777332366,
0.9994927644729614]],
'confidence': [0.9994927644729614]},
{'sentence': 'food was good and cheap .',
'IOB': ['B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['food', 'was', 'good', 'and', 'cheap', '.'],
'aspect': ['food'],
'position': [[0]],
'sentiment': ['Positive'],
'probs': [[0.0001491083239670843, 0.000637161429040134, 0.999213695526123]],
'confidence': [0.999213695526123]},
{'sentence': 'i had the kafta plate and i enjoyed it .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['i',
'had',
'the',
'kafta',
'plate',
'and',
'i',
'enjoyed',
'it',
'.'],
'aspect': ['kafta'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.00012317451182752848,
0.0006539796595461667,
0.9992228746414185]],
'confidence': [0.9992228746414185]},
{'sentence': 'atmosphere was nice .',
'IOB': ['B-ASP', 'O', 'O', 'O'],
'tokens': ['atmosphere', 'was', 'nice', '.'],
'aspect': ['atmosphere'],
'position': [[0]],
'sentiment': ['Positive'],
'probs': [[0.00015691579028498381, 0.002661335514858365, 0.99718177318573]],
'confidence': [0.99718177318573]},
{'sentence': "service was kind of slow , our waitress took forever to give us our check even though it was n ' t that busy .",
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['service',
'was',
'kind',
'of',
'slow',
',',
'our',
'waitress',
'took',
'forever',
'to',
'give',
'us',
'our',
'check',
'even',
'though',
'it',
'was',
'n',
"'",
't',
'that',
'busy',
'.'],
'aspect': ['service', 'waitress'],
'position': [[0, 7], [0, 7]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9986470341682434, 0.00112546281889081, 0.000227475626161322],
[0.998261034488678, 0.0015556818107143044, 0.00018331260071136057]],
'confidence': [0.9986470341682434, 0.998261034488678]},
{'sentence': 'still i would recommend this place .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['still', 'i', 'would', 'recommend', 'this', 'place', '.'],
'aspect': ['place'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.0006818865658715367,
0.00021724606631323695,
0.999100923538208]],
'confidence': [0.999100923538208]},
{'sentence': 'what else can you say nice people amazing food wow',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['what',
'else',
'can',
'you',
'say',
'nice',
'people',
'amazing',
'food',
'wow'],
'aspect': ['food'],
'position': [[8]],
'sentiment': ['Positive'],
'probs': [[0.00026921508833765984,
0.0003282412944827229,
0.9994025230407715]],
'confidence': [0.9994025230407715]},
{'sentence': 'great food with an awesome atmosphere !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['great', 'food', 'with', 'an', 'awesome', 'atmosphere', '!'],
'aspect': ['food', 'atmosphere'],
'position': [[1, 5], [1, 5]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00023538662935607135,
0.0002400344528723508,
0.9995244741439819],
[0.00021667423425242305, 0.00023999162658583373, 0.9995433688163757]],
'confidence': [0.9995244741439819, 0.9995433688163757]},
{'sentence': ' – eggs , pancakes , potatoes , fresh fruit and yogurt - - everything they serve is delicious .',
'IOB': ['O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'eggs',
',',
'pancakes',
',',
'potatoes',
',',
'fresh',
'fruit',
'and',
'yogurt',
'-',
'-',
'everything',
'they',
'serve',
'is',
'delicious',
'.'],
'aspect': ['–', ',', ',', 'fresh', 'and'],
'position': [[1, 3, 5, 8, 10, 19],
[1, 3, 5, 8, 10, 19],
[1, 3, 5, 8, 10, 19],
[1, 3, 5, 8, 10, 19],
[1, 3, 5, 8, 10, 19]],
'sentiment': ['Neutral', 'Neutral', 'Neutral', 'Neutral', 'Positive'],
'probs': [[0.0004670051275752485, 0.977412760257721, 0.022120269015431404],
[0.00044351984979584813, 0.9747578501701355, 0.02479868195950985],
[0.00044351984979584813, 0.9747578501701355, 0.02479868195950985],
[0.00045504490844905376, 0.8132956624031067, 0.18624931573867798],
[0.000302033411571756, 0.13441713154315948, 0.8652808666229248]],
'confidence': [0.977412760257721,
0.9747578501701355,
0.9747578501701355,
0.8132956624031067,
0.8652808666229248]},
{'sentence': "the best place for a leisure sunday breakfast amidst yachts , then take a stroll through the nearby farmer ' s market .",
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'best',
'place',
'for',
'a',
'leisure',
'sunday',
'breakfast',
'amidst',
'yachts',
',',
'then',
'take',
'a',
'stroll',
'through',
'the',
'nearby',
'farmer',
"'",
's',
'market',
'.'],
'aspect': ['place', 'breakfast'],
'position': [[2, 7], [2, 7]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0002989010536111891, 0.0004214474465698004, 0.9992796778678894],
[0.0007204548455774784, 0.6227761507034302, 0.3765033781528473]],
'confidence': [0.9992796778678894, 0.6227761507034302]},
{'sentence': 'great meal – the fish on the omikase platter was absolutely decadent - - there was none of the stringiness that sometimes accompanies fair sushi - - this fish was perfect ! ! ! !',
'IOB': ['O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['great',
'meal',
'–',
'the',
'fish',
'on',
'the',
'omikase',
'platter',
'was',
'absolutely',
'decadent',
'-',
'-',
'there',
'was',
'none',
'of',
'the',
'stringiness',
'that',
'sometimes',
'accompanies',
'fair',
'sushi',
'-',
'-',
'this',
'fish',
'was',
'perfect',
'!',
'!',
'!',
'!'],
'aspect': ['meal', 'fish', 'omikase platter', 'sushi'],
'position': [[1, 4, 7, 8, 24],
[1, 4, 7, 8, 24],
[1, 4, 7, 8, 24],
[1, 4, 7, 8, 24]],
'sentiment': ['Positive', 'Positive', 'Positive', 'Positive'],
'probs': [[0.0012784316204488277, 0.0005580794531852007, 0.9981635212898254],
[0.0012994208373129368, 0.0015174305299296975, 0.9971831440925598],
[0.00023512417101301253, 0.0015662281075492501, 0.9981986880302429],
[0.0004847263917326927, 0.30346158146858215, 0.696053683757782]],
'confidence': [0.9981635212898254,
0.9971831440925598,
0.9981986880302429,
0.696053683757782]},
{'sentence': "plus , i am allergic to rice , and the waitstaff was unbelievably accomodating - - did n ' t even bat an eye !",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['plus',
',',
'i',
'am',
'allergic',
'to',
'rice',
',',
'and',
'the',
'waitstaff',
'was',
'unbelievably',
'accomodating',
'-',
'-',
'did',
'n',
"'",
't',
'even',
'bat',
'an',
'eye',
'!'],
'aspect': ['rice', 'waitstaff'],
'position': [[6, 10], [6, 10]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0005301929195411503, 0.9988677501678467, 0.0006020625587552786],
[0.0004039335181005299, 0.00022548453125637025, 0.9993705153465271]],
'confidence': [0.9988677501678467, 0.9993705153465271]},
{'sentence': 'and the waiter suggested a perfect sake ! !',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['and',
'the',
'waiter',
'suggested',
'a',
'perfect',
'sake',
'!',
'!'],
'aspect': ['waiter', 'sake'],
'position': [[2, 6], [2, 6]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0002728269319050014, 0.9989742040634155, 0.0007530013099312782],
[0.0006182954530231655, 0.0002197421417804435, 0.999161958694458]],
'confidence': [0.9989742040634155, 0.999161958694458]},
{'sentence': 'unbeatable sushi !',
'IOB': ['O', 'B-ASP', 'O'],
'tokens': ['unbeatable', 'sushi', '!'],
'aspect': ['sushi'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00023391979630105197,
0.0002595169353298843,
0.9995065927505493]],
'confidence': [0.9995065927505493]},
{'sentence': 'melt in your mouth nigiri and sashmi , and very tasty rolls too .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O'],
'tokens': ['melt',
'in',
'your',
'mouth',
'nigiri',
'and',
'sashmi',
',',
'and',
'very',
'tasty',
'rolls',
'too',
'.'],
'aspect': ['nigiri', 'rolls'],
'position': [[4, 11], [4, 11]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0001955762127181515, 0.9989190101623535, 0.000885391200426966],
[0.0021417017560452223, 0.00018203345825895667, 0.9976761937141418]],
'confidence': [0.9989190101623535, 0.9976761937141418]},
{'sentence': 'be sure to try the oyster roll .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'I-ASP', 'O'],
'tokens': ['be', 'sure', 'to', 'try', 'the', 'oyster', 'roll', '.'],
'aspect': ['oyster roll'],
'position': [[5, 6]],
'sentiment': ['Positive'],
'probs': [[0.00019118981435894966,
0.00025342596927657723,
0.9995552897453308]],
'confidence': [0.9995552897453308]},
{'sentence': ' – how to describe the best sushi in nyc : hmmmm , delicious , amazing , fantastic , suculent , perfect , nah , all of the above .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'how',
'to',
'describe',
'the',
'best',
'sushi',
'in',
'nyc',
':',
'hmmmm',
',',
'delicious',
',',
'amazing',
',',
'fantastic',
',',
'suculent',
',',
'perfect',
',',
'nah',
',',
'all',
'of',
'the',
'above',
'.'],
'aspect': ['best'],
'position': [[6, 29]],
'sentiment': ['Positive'],
'probs': [[0.0002454328932799399, 0.002495987107977271, 0.9972586631774902]],
'confidence': [0.9972586631774902]},
{'sentence': "i ca n ' t saybenough good things about this restaurant , and i ca n ' t wait for my next several visits .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'ca',
'n',
"'",
't',
'saybenough',
'good',
'things',
'about',
'this',
'restaurant',
',',
'and',
'i',
'ca',
'n',
"'",
't',
'wait',
'for',
'my',
'next',
'several',
'visits',
'.'],
'aspect': ['restaurant'],
'position': [[10]],
'sentiment': ['Positive'],
'probs': [[0.0003472299431450665,
0.00024302510428242385,
0.9994097948074341]],
'confidence': [0.9994097948074341]},
{'sentence': 'the best chuwam mushi i have ever had .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'best',
'chuwam',
'mushi',
'i',
'have',
'ever',
'had',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'good sushi , high price',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP'],
'tokens': ['good', 'sushi', ',', 'high', 'price'],
'aspect': ['sushi', 'price'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.001278954092413187, 0.00033626193180680275, 0.9983848333358765],
[0.02979719080030918, 0.0005768953124061227, 0.9696258902549744]],
'confidence': [0.9983848333358765, 0.9696258902549744]},
{'sentence': 'one of the best sushi place in town .',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['one', 'of', 'the', 'best', 'sushi', 'place', 'in', 'town', '.'],
'aspect': ['sushi'],
'position': [[4]],
'sentiment': ['Positive'],
'probs': [[0.00022178371727932245,
0.0002540888963267207,
0.9995242357254028]],
'confidence': [0.9995242357254028]},
{'sentence': 'the house special roll is really good .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'house', 'special', 'roll', 'is', 'really', 'good', '.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'a cozy spot for Positive',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['a', 'cozy', 'spot', 'for', 'Positive'],
'aspect': ['spot'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00021072656090836972,
0.00031234085327014327,
0.999476969242096]],
'confidence': [0.999476969242096]},
{'sentence': " – i ca n ' t believe murphy ' s has been around for over 25 years , amazing .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'ca',
'n',
"'",
't',
'believe',
'murphy',
"'",
's',
'has',
'been',
'around',
'for',
'over',
'25',
'years',
',',
'amazing',
'.'],
'aspect': ['believe'],
'position': [[7, 20]],
'sentiment': ['Positive'],
'probs': [[0.0008910357719287276,
0.0002689045504666865,
0.9988401532173157]],
'confidence': [0.9988401532173157]},
{'sentence': "brunch at murphy ' s is to die for , my specialty . . . egg white omelet , the food is always freshly prepared .",
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['brunch',
'at',
'murphy',
"'",
's',
'is',
'to',
'die',
'for',
',',
'my',
'specialty',
'.',
'.',
'.',
'egg',
'white',
'omelet',
',',
'the',
'food',
'is',
'always',
'freshly',
'prepared',
'.'],
'aspect': ['brunch', 'egg white omelet', 'food'],
'position': [[0, 15, 16, 17, 20], [0, 15, 16, 17, 20], [0, 15, 16, 17, 20]],
'sentiment': ['Positive', 'Neutral', 'Positive'],
'probs': [[0.0003781156556215137, 0.0004958455101586878, 0.9991260170936584],
[0.0002026818401645869, 0.9686536192893982, 0.031143682077527046],
[0.00013715280510950834, 0.003584759309887886, 0.9962781071662903]],
'confidence': [0.9991260170936584, 0.9686536192893982, 0.9962781071662903]},
{'sentence': "it ' s the perfect spot for a romantic date for 2 or a secret rendezvous !",
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['it',
"'",
's',
'the',
'perfect',
'spot',
'for',
'a',
'romantic',
'date',
'for',
'2',
'or',
'a',
'secret',
'rendezvous',
'!'],
'aspect': ['spot'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.00024608077364973724,
0.00022879552852828056,
0.9995251893997192]],
'confidence': [0.9995251893997192]},
{'sentence': 'save room for scrumptious desserts .',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['save', 'room', 'for', 'scrumptious', 'desserts', '.'],
'aspect': ['desserts'],
'position': [[4]],
'sentiment': ['Positive'],
'probs': [[0.0003241470258217305,
0.00026327770319767296,
0.9994125366210938]],
'confidence': [0.9994125366210938]},
{'sentence': "the restaurant offers an extensive wine list and an ambiance you wo n ' t forget !",
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'restaurant',
'offers',
'an',
'extensive',
'wine',
'list',
'and',
'an',
'ambiance',
'you',
'wo',
'n',
"'",
't',
'forget',
'!'],
'aspect': ['wine list', 'ambiance'],
'position': [[5, 6, 9], [5, 6, 9]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00010879179899347946,
0.0024530631490051746,
0.9974380731582642],
[0.0001987445866689086, 0.0003876987611874938, 0.9994136095046997]],
'confidence': [0.9974380731582642, 0.9994136095046997]},
{'sentence': ' – best mexican place for lunch in the financial district .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'best',
'mexican',
'place',
'for',
'lunch',
'in',
'the',
'financial',
'district',
'.'],
'aspect': ['mexican', 'for'],
'position': [[3, 5, 11], [3, 5, 11]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002624496992211789, 0.0033930817153304815, 0.9963443875312805],
[0.0003362944698892534, 0.10115893185138702, 0.8985047340393066]],
'confidence': [0.9963443875312805, 0.8985047340393066]},
{'sentence': 'love the enchiladas and chicken soup - and be sure to check out their specials .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['love',
'the',
'enchiladas',
'and',
'chicken',
'soup',
'-',
'and',
'be',
'sure',
'to',
'check',
'out',
'their',
'specials',
'.'],
'aspect': ['enchiladas', 'chicken soup', 'specials'],
'position': [[2, 4, 5, 14], [2, 4, 5, 14], [2, 4, 5, 14]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.0004160322423558682, 0.0002376902411924675, 0.9993463158607483],
[0.0002455458452459425, 0.00024535018019378185, 0.9995090961456299],
[0.000213230203371495, 0.12224218994379044, 0.877544641494751]],
'confidence': [0.9993463158607483, 0.9995090961456299, 0.877544641494751]},
{'sentence': 'the cooks have been at the restaurant for years and cook family recipes .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'cooks',
'have',
'been',
'at',
'the',
'restaurant',
'for',
'years',
'and',
'cook',
'family',
'recipes',
'.'],
'aspect': ['cooks', 'recipes'],
'position': [[1, 12], [1, 12]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0022843824699521065, 0.28085824847221375, 0.7168573141098022],
[0.00044969943701289594, 0.6564095616340637, 0.34314075112342834]],
'confidence': [0.7168573141098022, 0.6564095616340637]},
{'sentence': 'can get busy on fridays for a table but once seated , the service is so efficient you can be in and out of there quickly .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['can',
'get',
'busy',
'on',
'fridays',
'for',
'a',
'table',
'but',
'once',
'seated',
',',
'the',
'service',
'is',
'so',
'efficient',
'you',
'can',
'be',
'in',
'and',
'out',
'of',
'there',
'quickly',
'.'],
'aspect': ['table', 'service'],
'position': [[7, 13], [7, 13]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0003687399730551988, 0.9988006353378296, 0.0008306285599246621],
[0.00030604927451349795, 0.00023733070702292025, 0.9994565844535828]],
'confidence': [0.9988006353378296, 0.9994565844535828]},
{'sentence': 'the sushi was excellent and the wait staff was quick .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'B-ASP', 'I-ASP', 'O', 'O', 'O'],
'tokens': ['the',
'sushi',
'was',
'excellent',
'and',
'the',
'wait',
'staff',
'was',
'quick',
'.'],
'aspect': ['sushi', 'wait staff'],
'position': [[1, 6, 7], [1, 6, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00023951116600073874,
0.00024694728199392557,
0.9995135068893433],
[0.00017478609515819699, 0.0002586348564364016, 0.9995664954185486]],
'confidence': [0.9995135068893433, 0.9995664954185486]},
{'sentence': 'the atmosphere was just okay .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'atmosphere', 'was', 'just', 'okay', '.'],
'aspect': ['atmosphere'],
'position': [[1]],
'sentiment': ['Neutral'],
'probs': [[0.027062654495239258, 0.9435452818870544, 0.029392104595899582]],
'confidence': [0.9435452818870544]},
{'sentence': 'space was limited , but the food made up for it .',
'IOB': ['B-ASP', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['space',
'was',
'limited',
',',
'but',
'the',
'food',
'made',
'up',
'for',
'it',
'.'],
'aspect': ['space', 'food'],
'position': [[0, 6], [0, 6]],
'sentiment': ['Negative', 'Positive'],
'probs': [[0.9941558837890625, 0.005653759464621544, 0.0001903702359413728],
[0.0005110310739837587, 0.0004274933598935604, 0.9990615248680115]],
'confidence': [0.9941558837890625, 0.9990615248680115]},
{'sentence': "well i guess it ' s hard to be seated when one is invisible to the staff .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['well',
'i',
'guess',
'it',
"'",
's',
'hard',
'to',
'be',
'seated',
'when',
'one',
'is',
'invisible',
'to',
'the',
'staff',
'.'],
'aspect': ['staff'],
'position': [[16]],
'sentiment': ['Negative'],
'probs': [[0.9861141443252563, 0.013355452567338943, 0.0005303607904352248]],
'confidence': [0.9861141443252563]},
{'sentence': 'we stood there for 10 minutes while employees walked back and forth ignoring us .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['we',
'stood',
'there',
'for',
'10',
'minutes',
'while',
'employees',
'walked',
'back',
'and',
'forth',
'ignoring',
'us',
'.'],
'aspect': ['employees'],
'position': [[7]],
'sentiment': ['Negative'],
'probs': [[0.9949439167976379,
0.004799911752343178,
0.00025618996005505323]],
'confidence': [0.9949439167976379]},
{'sentence': 'finally , my wife stood face to face in front of one of the staff and she asked , " are you waiting for a table ? "',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O'],
'tokens': ['finally',
',',
'my',
'wife',
'stood',
'face',
'to',
'face',
'in',
'front',
'of',
'one',
'of',
'the',
'staff',
'and',
'she',
'asked',
',',
'"',
'are',
'you',
'waiting',
'for',
'a',
'table',
'?',
'"'],
'aspect': ['staff', 'waiting', 'table'],
'position': [[14, 22, 25], [14, 22, 25], [14, 22, 25]],
'sentiment': ['Negative', 'Neutral', 'Neutral'],
'probs': [[0.9988186955451965,
0.00034627728746272624,
0.0008350596763193607],
[0.0018864523153752089, 0.9976840019226074, 0.000429480685852468],
[0.0002728799299802631, 0.9991663694381714, 0.0005608284845948219]],
'confidence': [0.9988186955451965, 0.9976840019226074, 0.9991663694381714]},
{'sentence': "the caesar salad i ordered had so much lemon i could n ' t eat it .",
'IOB': ['O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'caesar',
'salad',
'i',
'ordered',
'had',
'so',
'much',
'lemon',
'i',
'could',
'n',
"'",
't',
'eat',
'it',
'.'],
'aspect': ['caesar salad', 'lemon'],
'position': [[1, 2, 8], [1, 2, 8]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.16001030802726746, 0.8397173881530762, 0.00027227139798924327],
[0.9967079162597656, 0.00026033888570964336, 0.003031714353710413]],
'confidence': [0.8397173881530762, 0.9967079162597656]},
{'sentence': 'great food , better margaritas !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['great', 'food', ',', 'better', 'margaritas', '!'],
'aspect': ['food', 'margaritas'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002553928061388433, 0.00026972618070431054, 0.999474823474884],
[0.00023830367717891932, 0.00027653176221065223, 0.9994851350784302]],
'confidence': [0.999474823474884, 0.9994851350784302]},
{'sentence': ' – this is one of my top lunch spots , huge portions , fast service and amazing margaritas ! !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'this',
'is',
'one',
'of',
'my',
'top',
'lunch',
'spots',
',',
'huge',
'portions',
',',
'fast',
'service',
'and',
'amazing',
'margaritas',
'!',
'!'],
'aspect': ['top lunch', 'huge', 'fast', 'amazing'],
'position': [[7, 8, 11, 14, 17, 20],
[7, 8, 11, 14, 17, 20],
[7, 8, 11, 14, 17, 20],
[7, 8, 11, 14, 17, 20]],
'sentiment': ['Neutral', 'Positive', 'Positive', 'Positive'],
'probs': [[0.0002670780522748828, 0.8716978430747986, 0.1280350685119629],
[0.00017180141003336757, 0.008834988810122013, 0.9909932017326355],
[0.00020396840409375727, 0.0003101435722783208, 0.9994858503341675],
[0.00038332620169967413, 0.00020245059567969292, 0.999414324760437]],
'confidence': [0.8716978430747986,
0.9909932017326355,
0.9994858503341675,
0.999414324760437]},
{'sentence': 'it gets really busy , so get there on the early side so you can grab a seat , if you do have to wait , its not bad because the service is quick !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['it',
'gets',
'really',
'busy',
',',
'so',
'get',
'there',
'on',
'the',
'early',
'side',
'so',
'you',
'can',
'grab',
'a',
'seat',
',',
'if',
'you',
'do',
'have',
'to',
'wait',
',',
'its',
'not',
'bad',
'because',
'the',
'service',
'is',
'quick',
'!'],
'aspect': ['seat', 'service'],
'position': [[17, 31], [17, 31]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00029364056535996497, 0.9985530972480774, 0.001153203658759594],
[0.001182383974082768, 0.0001981524983420968, 0.9986194372177124]],
'confidence': [0.9985530972480774, 0.9986194372177124]},
{'sentence': 'check out the art on the walls , very colorful !',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['check',
'out',
'the',
'art',
'on',
'the',
'walls',
',',
'very',
'colorful',
'!'],
'aspect': ['art'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.0002140652941307053,
0.0003095794527325779,
0.9994763731956482]],
'confidence': [0.9994763731956482]},
{'sentence': 'i love this place !',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['i', 'love', 'this', 'place', '!'],
'aspect': ['place'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.0002865414135158062,
0.00022958296176511794,
0.9994838237762451]],
'confidence': [0.9994838237762451]},
{'sentence': ' – i have been eating at this place for over 8 years now and i have never had one bad meal .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'have',
'been',
'eating',
'at',
'this',
'place',
'for',
'over',
'8',
'years',
'now',
'and',
'i',
'have',
'never',
'had',
'one',
'bad',
'meal',
'.'],
'aspect': ['bad'],
'position': [[20, 22]],
'sentiment': ['Positive'],
'probs': [[0.00021976947027724236,
0.0003224597021471709,
0.9994577765464783]],
'confidence': [0.9994577765464783]},
{'sentence': 'i highly recommend this place to all that want to try indain food for the first time .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'highly',
'recommend',
'this',
'place',
'to',
'all',
'that',
'want',
'to',
'try',
'indain',
'food',
'for',
'the',
'first',
'time',
'.'],
'aspect': ['indain food'],
'position': [[11, 12]],
'sentiment': ['Positive'],
'probs': [[0.00011198962602065876,
0.0008482279372401536,
0.9990398287773132]],
'confidence': [0.9990398287773132]},
{'sentence': 'the lunch menu is an awesome deal !',
'IOB': ['O', 'B-ASP', 'I-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'lunch', 'menu', 'is', 'an', 'awesome', 'deal', '!'],
'aspect': ['lunch menu'],
'position': [[1, 2]],
'sentiment': ['Positive'],
'probs': [[0.00019342357700224966,
0.00027133440016768873,
0.999535322189331]],
'confidence': [0.999535322189331]},
{'sentence': 'plenty of food , trust me .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['plenty', 'of', 'food', ',', 'trust', 'me', '.'],
'aspect': ['food'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.0001721205480862409,
0.00043518951861187816,
0.9993926286697388]],
'confidence': [0.9993926286697388]},
{'sentence': 'fresh ingrediants and super tasty .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['fresh', 'ingrediants', 'and', 'super', 'tasty', '.'],
'aspect': ['ingrediants'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0003564557700883597,
0.00021880025451537222,
0.9994248151779175]],
'confidence': [0.9994248151779175]},
{'sentence': 'best food , phenominal service',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP'],
'tokens': ['best', 'food', ',', 'phenominal', 'service'],
'aspect': ['food', 'service'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002511751081328839, 0.0002390709996689111, 0.9995098114013672],
[0.00022671888291370124, 0.0002516504027880728, 0.9995216131210327]],
'confidence': [0.9995098114013672, 0.9995216131210327]},
{'sentence': 'for the finicky sushi eater and those who have sampled the best nyc has to offer , the fish is the freshest and the service is superb .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['for',
'the',
'finicky',
'sushi',
'eater',
'and',
'those',
'who',
'have',
'sampled',
'the',
'best',
'nyc',
'has',
'to',
'offer',
',',
'the',
'fish',
'is',
'the',
'freshest',
'and',
'the',
'service',
'is',
'superb',
'.'],
'aspect': ['sushi', 'fish', 'service'],
'position': [[3, 18, 24], [3, 18, 24], [3, 18, 24]],
'sentiment': ['Neutral', 'Positive', 'Positive'],
'probs': [[0.00019516784232109785,
0.9983630776405334,
0.0014417067868635058],
[0.00022146961418911815, 0.00022394498228095472, 0.9995545744895935],
[0.0002649352536536753, 0.00020638825662899762, 0.9995287656784058]],
'confidence': [0.9983630776405334, 0.9995545744895935, 0.9995287656784058]},
{'sentence': "not only can the selection be innovative , but there ' s a nice balance of traditional sushi as well .",
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['not',
'only',
'can',
'the',
'selection',
'be',
'innovative',
',',
'but',
'there',
"'",
's',
'a',
'nice',
'balance',
'of',
'traditional',
'sushi',
'as',
'well',
'.'],
'aspect': ['selection', 'sushi'],
'position': [[4, 17], [4, 17]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0003636895853560418, 0.0003654824977274984, 0.9992708563804626],
[0.000292646000161767, 0.06685585528612137, 0.9328514337539673]],
'confidence': [0.9992708563804626, 0.9328514337539673]},
{'sentence': 'the nicest waiters in town .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the', 'nicest', 'waiters', 'in', 'town', '.'],
'aspect': ['waiters'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00020542589481920004, 0.0002828787546604872, 0.99951171875]],
'confidence': [0.99951171875]},
{'sentence': ' – this place is unbelievably over - rated .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', '[SEP]'],
'tokens': [' ',
'–',
'this',
'place',
'is',
'unbelievably',
'over',
'-',
'rated',
'.'],
'aspect': ['this'],
'position': [[2, 9]],
'sentiment': ['Negative'],
'probs': [[0.9991658926010132,
0.0005885598948225379,
0.0002455959329381585]],
'confidence': [0.9991658926010132]},
{'sentence': "if i want to stand in line on sunday for an hour to get average brunch food , then i would put murphy ' s at the top of the list .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['if',
'i',
'want',
'to',
'stand',
'in',
'line',
'on',
'sunday',
'for',
'an',
'hour',
'to',
'get',
'average',
'brunch',
'food',
',',
'then',
'i',
'would',
'put',
'murphy',
"'",
's',
'at',
'the',
'top',
'of',
'the',
'list',
'.'],
'aspect': ['brunch food'],
'position': [[15, 16]],
'sentiment': ['Neutral'],
'probs': [[0.010183390229940414, 0.9892593622207642, 0.0005572233931161463]],
'confidence': [0.9892593622207642]},
{'sentence': 'the regular menu here is slightly above average that is not worth the snotty attitude that you receive .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'regular',
'menu',
'here',
'is',
'slightly',
'above',
'average',
'that',
'is',
'not',
'worth',
'the',
'snotty',
'attitude',
'that',
'you',
'receive',
'.'],
'aspect': ['menu', 'attitude'],
'position': [[2, 14], [2, 14]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.00023518185480497777,
0.9986911416053772,
0.0010736772092059255],
[0.999243974685669, 0.0003181504434905946, 0.00043783042929135263]],
'confidence': [0.9986911416053772, 0.999243974685669]},
{'sentence': 'your a sushi fan , you love expertly cut fish , great sake , a killer soho location , and of course : salmon , tuna , fluke , yellow tail , cod , mackeral , jellyfish , sea urchin , shrimp , lobster , sea bream , trout , milk fish , blue fin tuna , eel , crab , sardine , monk fish , roe , scallop , oysters , and a varity of toro .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['your',
'a',
'sushi',
'fan',
',',
'you',
'love',
'expertly',
'cut',
'fish',
',',
'great',
'sake',
',',
'a',
'killer',
'soho',
'location',
',',
'and',
'of',
'course',
':',
'salmon',
',',
'tuna',
',',
'fluke',
',',
'yellow',
'tail',
',',
'cod',
',',
'mackeral',
',',
'jellyfish',
',',
'sea',
'urchin',
',',
'shrimp',
',',
'lobster',
',',
'sea',
'bream',
',',
'trout',
',',
'milk',
'fish',
',',
'blue',
'fin',
'tuna',
',',
'eel',
',',
'crab',
',',
'sardine',
',',
'monk',
'fish',
',',
'roe',
',',
'scallop',
',',
'oysters',
',',
'and',
'a',
'varity',
'of',
'toro',
'.'],
'aspect': ['sushi',
'sake',
'soho location',
'salmon',
'yellow tail',
'cod',
'mackeral',
'jellyfish',
'sea urchin',
'shrimp',
'lobster',
'sea bream',
'trout',
'blue fin tuna',
'eel',
'crab',
'sardine',
'monk fish',
'roe',
'scallop',
'oysters'],
'position': [[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
36,
38,
39,
41,
43,
45,
46,
48,
53,
54,
55,
57,
59,
61,
63,
64,
66,
68,
70]],
'sentiment': ['Positive',
'Positive',
'Positive',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral'],
'probs': [[0.00047447369433939457, 0.20655153691768646, 0.7929739952087402],
[0.00039202874177135527, 0.001868992461822927, 0.9977389574050903],
[0.0003530100220814347, 0.0013654835056513548, 0.9982815980911255],
[0.0007483495282940567, 0.9958761930465698, 0.0033753940369933844],
[0.0017039576778188348, 0.9976828098297119, 0.0006131980917416513],
[0.003810115624219179, 0.9955565333366394, 0.0006334170466288924],
[0.0037933506537228823, 0.995719850063324, 0.0004868003015872091],
[0.006777883507311344, 0.9926003813743591, 0.0006216719630174339],
[0.006769354920834303, 0.9925959706306458, 0.0006346748559735715],
[0.0066869426518678665, 0.9925472140312195, 0.0007658426184207201],
[0.0069373007863759995, 0.9922177791595459, 0.0008449580636806786],
[0.006625615991652012, 0.9925268888473511, 0.0008475516806356609],
[0.007691710721701384, 0.9913954138755798, 0.0009128708043135703],
[0.004557103384286165, 0.9947675466537476, 0.0006753305206075311],
[0.005787232890725136, 0.9934631586074829, 0.0007495781756006181],
[0.004404751118272543, 0.9947691559791565, 0.000826117757242173],
[0.0030164308845996857, 0.9959264993667603, 0.001057095592841506],
[0.0022708007600158453, 0.9904173612594604, 0.007311907131224871],
[0.0008583605522289872, 0.9916669726371765, 0.0074747297912836075],
[0.0008115122327581048, 0.9698216319084167, 0.029366832226514816],
[0.0010589472949504852, 0.894161581993103, 0.1047794446349144]],
'confidence': [0.7929739952087402,
0.9977389574050903,
0.9982815980911255,
0.9958761930465698,
0.9976828098297119,
0.9955565333366394,
0.995719850063324,
0.9926003813743591,
0.9925959706306458,
0.9925472140312195,
0.9922177791595459,
0.9925268888473511,
0.9913954138755798,
0.9947675466537476,
0.9934631586074829,
0.9947691559791565,
0.9959264993667603,
0.9904173612594604,
0.9916669726371765,
0.9698216319084167,
0.894161581993103]},
{'sentence': 'your a sushi fan , you love expertly cut fish , great sake , a killer soho location , and of course : salmon , tuna , fluke , yellow tail , cod , mackeral , jelly $ t $ , sea urchin , shrimp , lobster , sea bream , trout , milk fish , blue fin tuna , eel , crab , sardine , monk fish , roe , scallop , oysters , and a varity of toro .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['your',
'a',
'sushi',
'fan',
',',
'you',
'love',
'expertly',
'cut',
'fish',
',',
'great',
'sake',
',',
'a',
'killer',
'soho',
'location',
',',
'and',
'of',
'course',
':',
'salmon',
',',
'tuna',
',',
'fluke',
',',
'yellow',
'tail',
',',
'cod',
',',
'mackeral',
',',
'jelly',
'$',
't',
'$',
',',
'sea',
'urchin',
',',
'shrimp',
',',
'lobster',
',',
'sea',
'bream',
',',
'trout',
',',
'milk',
'fish',
',',
'blue',
'fin',
'tuna',
',',
'eel',
',',
'crab',
',',
'sardine',
',',
'monk',
'fish',
',',
'roe',
',',
'scallop',
',',
'oysters',
',',
'and',
'a',
'varity',
'of',
'toro',
'.'],
'aspect': ['sushi',
'sake',
'soho location',
'salmon',
'yellow tail',
'cod',
'mackeral',
'sea urchin',
'shrimp',
'lobster',
'sea bream',
'trout',
'blue fin tuna',
'eel',
'crab',
'sardine',
'monk fish',
'roe',
'scallop',
'oysters'],
'position': [[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73],
[2,
12,
16,
17,
23,
29,
30,
32,
34,
41,
42,
44,
46,
48,
49,
51,
56,
57,
58,
60,
62,
64,
66,
67,
69,
71,
73]],
'sentiment': ['Positive',
'Positive',
'Positive',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Neutral'],
'probs': [[0.0004637014935724437, 0.18194961547851562, 0.8175867199897766],
[0.0003743496199604124, 0.002018987201154232, 0.997606635093689],
[0.0003620455681812018, 0.0017690833192318678, 0.9978687763214111],
[0.0007194189820438623, 0.9958772659301758, 0.0034033511765301228],
[0.001131539698690176, 0.9982738494873047, 0.0005945933517068624],
[0.001644914853386581, 0.9977626800537109, 0.0005924006109125912],
[0.0016408192459493876, 0.997905969619751, 0.0004531741433311254],
[0.0033064214512705803, 0.9961056113243103, 0.0005878998781554401],
[0.00401617307215929, 0.995287299156189, 0.0006965504726395011],
[0.004780106712132692, 0.9944586753845215, 0.0007612121989950538],
[0.0051840804517269135, 0.9940476417541504, 0.0007682617288082838],
[0.006546743679791689, 0.9926155805587769, 0.0008376635378226638],
[0.00465500820428133, 0.9946759939193726, 0.0006689475267194211],
[0.005899080540984869, 0.9933333992958069, 0.0007675588130950928],
[0.004562524612993002, 0.9945764541625977, 0.0008609640062786639],
[0.003171888878569007, 0.995703399181366, 0.0011247317306697369],
[0.002522422932088375, 0.989692747592926, 0.0077848853543400764],
[0.0009467342752031982, 0.9901703000068665, 0.00888290349394083],
[0.0009185604867525399, 0.9624527096748352, 0.036628659814596176],
[0.0012195877498015761, 0.8653944134712219, 0.13338603079319]],
'confidence': [0.8175867199897766,
0.997606635093689,
0.9978687763214111,
0.9958772659301758,
0.9982738494873047,
0.9977626800537109,
0.997905969619751,
0.9961056113243103,
0.995287299156189,
0.9944586753845215,
0.9940476417541504,
0.9926155805587769,
0.9946759939193726,
0.9933333992958069,
0.9945764541625977,
0.995703399181366,
0.989692747592926,
0.9901703000068665,
0.9624527096748352,
0.8653944134712219]},
{'sentence': 'there is only one place on the east coast that has it all , plus a lot more .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['there',
'is',
'only',
'one',
'place',
'on',
'the',
'east',
'coast',
'that',
'has',
'it',
'all',
',',
'plus',
'a',
'lot',
'more',
'.'],
'aspect': ['place'],
'position': [[4]],
'sentiment': ['Positive'],
'probs': [[0.00027503439923748374,
0.0002993190137203783,
0.9994257688522339]],
'confidence': [0.9994257688522339]},
{'sentence': 'bring your cell phone cause you may have to wait to get into the best sushi restaurant in the world : blue ribbon sushi .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['bring',
'your',
'cell',
'phone',
'cause',
'you',
'may',
'have',
'to',
'wait',
'to',
'get',
'into',
'the',
'best',
'sushi',
'restaurant',
'in',
'the',
'world',
':',
'blue',
'ribbon',
'sushi',
'.'],
'aspect': ['sushi'],
'position': [[15]],
'sentiment': ['Positive'],
'probs': [[0.0010705320164561272,
0.00018724985420703888,
0.9987421631813049]],
'confidence': [0.9987421631813049]},
{'sentence': 'hands down , the best tuna i have ever had .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['hands',
'down',
',',
'the',
'best',
'tuna',
'i',
'have',
'ever',
'had',
'.'],
'aspect': ['tuna'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.00025026072398759425,
0.00022703548893332481,
0.9995228052139282]],
'confidence': [0.9995228052139282]},
{'sentence': "blue ribbon lives up to it ' s fantastic reputation .",
'IOB': ['B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['blue',
'ribbon',
'lives',
'up',
'to',
'it',
"'",
's',
'fantastic',
'reputation',
'.'],
'aspect': ['blue'],
'position': [[0]],
'sentiment': ['Positive'],
'probs': [[0.00014571083011105657, 0.01009673997759819, 0.9897575378417969]],
'confidence': [0.9897575378417969]},
{'sentence': 'great value sushi with high quality & nice setting .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['great',
'value',
'sushi',
'with',
'high',
'quality',
'&',
'nice',
'setting',
'.'],
'aspect': ['sushi', 'setting'],
'position': [[2, 8], [2, 8]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00017579190898686647, 0.007180135231465101, 0.9926440119743347],
[0.00024056438996922225, 0.0002603205794002861, 0.9994990825653076]],
'confidence': [0.9926440119743347, 0.9994990825653076]},
{'sentence': "try the chef ' s choice for sushi as the smoked yellowtail was incredible and the rolls were also tasty .",
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['try',
'the',
'chef',
"'",
's',
'choice',
'for',
'sushi',
'as',
'the',
'smoked',
'yellowtail',
'was',
'incredible',
'and',
'the',
'rolls',
'were',
'also',
'tasty',
'.'],
'aspect': ['chef', 'sushi', 'smoked yellowtail', 'rolls'],
'position': [[2, 7, 10, 11, 16],
[2, 7, 10, 11, 16],
[2, 7, 10, 11, 16],
[2, 7, 10, 11, 16]],
'sentiment': ['Neutral', 'Neutral', 'Positive', 'Positive'],
'probs': [[0.00023035798221826553, 0.9905477166175842, 0.009221888147294521],
[0.0002762296935543418, 0.9535788297653198, 0.04614492878317833],
[0.00023662792227696627, 0.00029888105927966535, 0.9994644522666931],
[0.0007403873605653644, 0.0002315788879059255, 0.9990279674530029]],
'confidence': [0.9905477166175842,
0.9535788297653198,
0.9994644522666931,
0.9990279674530029]},
{'sentence': 'poor customer service / poor pizza .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['poor', 'customer', 'service', '/', 'poor', 'pizza', '.'],
'aspect': ['pizza'],
'position': [[5]],
'sentiment': ['Negative'],
'probs': [[0.999129593372345, 0.0006595858721993864, 0.0002108506887452677]],
'confidence': [0.999129593372345]},
{'sentence': 'poor customer service / poor pizza .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['poor', 'customer', 'service', '/', 'poor', 'pizza', '.'],
'aspect': ['pizza'],
'position': [[5]],
'sentiment': ['Negative'],
'probs': [[0.999129593372345, 0.0006595858721993864, 0.0002108506887452677]],
'confidence': [0.999129593372345]},
{'sentence': " – as with most restaurants in seattle , mioposto ' s service was bad and the food was overpriced .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'as',
'with',
'most',
'restaurants',
'in',
'seattle',
',',
'mioposto',
"'",
's',
'service',
'was',
'bad',
'and',
'the',
'food',
'was',
'overpriced',
'.'],
'aspect': ['s', 'the'],
'position': [[11, 16, 20], [11, 16, 20]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9879504442214966, 0.011193801648914814, 0.0008557547116652131],
[0.9957004189491272, 0.003995872102677822, 0.0003036808629985899]],
'confidence': [0.9879504442214966, 0.9957004189491272]},
{'sentence': "i know many people have their favorite types of pizza and pizza places , but mioposto ' s pizza lacks quality and good taste .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['i',
'know',
'many',
'people',
'have',
'their',
'favorite',
'types',
'of',
'pizza',
'and',
'pizza',
'places',
',',
'but',
'mioposto',
"'",
's',
'pizza',
'lacks',
'quality',
'and',
'good',
'taste',
'.'],
'aspect': ['pizza', 'places', 'quality', 'taste'],
'position': [[9, 12, 20, 23],
[9, 12, 20, 23],
[9, 12, 20, 23],
[9, 12, 20, 23]],
'sentiment': ['Positive', 'Positive', 'Negative', 'Negative'],
'probs': [[0.04253143072128296, 0.04628348350524902, 0.9111851453781128],
[0.12365298718214035, 0.20489166676998138, 0.6714553833007812],
[0.9850552082061768, 0.012811887077987194, 0.002132904715836048],
[0.9832823872566223, 0.013795263133943081, 0.0029223167803138494]],
'confidence': [0.9111851453781128,
0.6714553833007812,
0.9850552082061768,
0.9832823872566223]},
{'sentence': "to be honest , i ' ve had better frozen pizza .",
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['to',
'be',
'honest',
',',
'i',
"'",
've',
'had',
'better',
'frozen',
'pizza',
'.'],
'aspect': ['pizza'],
'position': [[10]],
'sentiment': ['Positive'],
'probs': [[0.0004671851929742843, 0.030574699863791466, 0.9689580202102661]],
'confidence': [0.9689580202102661]},
{'sentence': 'the only positive thing about mioposto is the nice location .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['the',
'only',
'positive',
'thing',
'about',
'mioposto',
'is',
'the',
'nice',
'location',
'.'],
'aspect': ['location'],
'position': [[9]],
'sentiment': ['Positive'],
'probs': [[0.0002020640386035666,
0.00029117512167431414,
0.9995067119598389]],
'confidence': [0.9995067119598389]},
{'sentence': "i was frankly shocked when i read the bad reviews - this place is fantastic ; it has not let us down in any way , and we ' ve eaten here more than 10 times .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'was',
'frankly',
'shocked',
'when',
'i',
'read',
'the',
'bad',
'reviews',
'-',
'this',
'place',
'is',
'fantastic',
';',
'it',
'has',
'not',
'let',
'us',
'down',
'in',
'any',
'way',
',',
'and',
'we',
"'",
've',
'eaten',
'here',
'more',
'than',
'10',
'times',
'.'],
'aspect': ['place'],
'position': [[12]],
'sentiment': ['Positive'],
'probs': [[0.00047747811186127365,
0.0002214130072388798,
0.9993010759353638]],
'confidence': [0.9993010759353638]},
{'sentence': "the food is fantastic , and the waiting staff has been perfect every single time we ' ve been there .",
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'food',
'is',
'fantastic',
',',
'and',
'the',
'waiting',
'staff',
'has',
'been',
'perfect',
'every',
'single',
'time',
'we',
"'",
've',
'been',
'there',
'.'],
'aspect': ['food', 'waiting staff'],
'position': [[1, 7, 8], [1, 7, 8]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00028765510069206357,
0.0002766124962363392,
0.9994357228279114],
[0.0002031417388934642, 0.0002541949215810746, 0.9995427131652832]],
'confidence': [0.9994357228279114, 0.9995427131652832]},
{'sentence': 'the only problem would be the wait , but we usually just have a drink in the front while waiting .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'only',
'problem',
'would',
'be',
'the',
'wait',
',',
'but',
'we',
'usually',
'just',
'have',
'a',
'drink',
'in',
'the',
'front',
'while',
'waiting',
'.'],
'aspect': ['wait', 'drink'],
'position': [[6, 14], [6, 14]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9939336180686951, 0.005451435688883066, 0.0006149937398731709],
[0.0005095499218441546, 0.9987408518791199, 0.000749656988773495]],
'confidence': [0.9939336180686951, 0.9987408518791199]},
{'sentence': 'seafood plus',
'IOB': ['B-ASP', 'O'],
'tokens': ['seafood', 'plus'],
'aspect': ['seafood'],
'position': [[0]],
'sentiment': ['Neutral'],
'probs': [[0.0032452172599732876, 0.6594339609146118, 0.33732083439826965]],
'confidence': [0.6594339609146118]},
{'sentence': 'the appetizer of oysters , lobster , crab ( small size ) made a perfect entre for my wife .',
'IOB': ['O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'appetizer',
'of',
'oysters',
',',
'lobster',
',',
'crab',
'(',
'small',
'size',
')',
'made',
'a',
'perfect',
'entre',
'for',
'my',
'wife',
'.'],
'aspect': ['appetizer of oysters', 'lobster', 'entre'],
'position': [[1, 2, 3, 5, 15], [1, 2, 3, 5, 15], [1, 2, 3, 5, 15]],
'sentiment': ['Positive', 'Neutral', 'Positive'],
'probs': [[0.000727239006664604, 0.014403590932488441, 0.9848692417144775],
[0.09755808115005493, 0.8960690498352051, 0.006372814532369375],
[0.010913105681538582, 0.0008796345209702849, 0.9882072806358337]],
'confidence': [0.9848692417144775, 0.8960690498352051, 0.9882072806358337]},
{'sentence': 'seabass on lobster risotto was the best .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['seabass', 'on', 'lobster', 'risotto', 'was', 'the', 'best', '.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'caesar salad was superb .',
'IOB': ['B-ASP', 'I-ASP', 'O', 'O', 'O'],
'tokens': ['caesar', 'salad', 'was', 'superb', '.'],
'aspect': ['caesar salad'],
'position': [[0, 1]],
'sentiment': ['Positive'],
'probs': [[0.00015389469626825303,
0.00035840028431266546,
0.9994876384735107]],
'confidence': [0.9994876384735107]},
{'sentence': 'great bottle of wine .',
'IOB': ['O', 'B-ASP', 'I-ASP', 'I-ASP', 'O'],
'tokens': ['great', 'bottle', 'of', 'wine', '.'],
'aspect': ['bottle of wine'],
'position': [[1, 2, 3]],
'sentiment': ['Positive'],
'probs': [[0.0002528823970351368,
0.00024373795895371586,
0.9995033740997314]],
'confidence': [0.9995033740997314]},
{'sentence': 'leave room for dessert .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['leave', 'room', 'for', 'dessert', '.'],
'aspect': ['dessert'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.0009201340144500136, 0.17615057528018951, 0.8229293823242188]],
'confidence': [0.8229293823242188]},
{'sentence': 'the food was ok , but the service was so poor that the food was cold buy the time everyone in my party was served .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'food',
'was',
'ok',
',',
'but',
'the',
'service',
'was',
'so',
'poor',
'that',
'the',
'food',
'was',
'cold',
'buy',
'the',
'time',
'everyone',
'in',
'my',
'party',
'was',
'served',
'.'],
'aspect': ['service', 'served'],
'position': [[7, 24], [7, 24]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9861444234848022, 0.011556567624211311, 0.0022989290300756693],
[0.8754737973213196, 0.014396797865629196, 0.11012940108776093]],
'confidence': [0.9861444234848022, 0.8754737973213196]},
{'sentence': "we had a very hard time getting the waitress ' attention and finally had to get up and go inside to speak to a manager .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['we',
'had',
'a',
'very',
'hard',
'time',
'getting',
'the',
'waitress',
"'",
'attention',
'and',
'finally',
'had',
'to',
'get',
'up',
'and',
'go',
'inside',
'to',
'speak',
'to',
'a',
'manager',
'.'],
'aspect': ['waitress', 'manager'],
'position': [[8, 24], [8, 24]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9977699518203735,
0.0020306953229010105,
0.00019936534226872027],
[0.0003105656069237739, 0.9953195452690125, 0.004369908478111029]],
'confidence': [0.9977699518203735, 0.9953195452690125]},
{'sentence': 'as it turns out the owner was seated right next to us and when he came over to check on our problems was very dismissive and offered a token 20 % discount on our bill .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['as',
'it',
'turns',
'out',
'the',
'owner',
'was',
'seated',
'right',
'next',
'to',
'us',
'and',
'when',
'he',
'came',
'over',
'to',
'check',
'on',
'our',
'problems',
'was',
'very',
'dismissive',
'and',
'offered',
'a',
'token',
'20',
'%',
'discount',
'on',
'our',
'bill',
'.'],
'aspect': ['owner', 'bill'],
'position': [[5, 34], [5, 34]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9663660526275635, 0.0007419096655212343, 0.032892048358917236],
[0.0006091395625844598, 0.9989417195320129, 0.000449110462795943]],
'confidence': [0.9663660526275635, 0.9989417195320129]},
{'sentence': 'avoid the place',
'IOB': ['O', 'O', 'B-ASP'],
'tokens': ['avoid', 'the', 'place'],
'aspect': ['place'],
'position': [[2]],
'sentiment': ['Negative'],
'probs': [[0.9991046786308289,
0.0003963171038776636,
0.0004989578737877309]],
'confidence': [0.9991046786308289]},
{'sentence': 'when i got there i sat up stairs where the atmosphere was cozy & the service was horrible !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['when',
'i',
'got',
'there',
'i',
'sat',
'up',
'stairs',
'where',
'the',
'atmosphere',
'was',
'cozy',
'&',
'the',
'service',
'was',
'horrible',
'!'],
'aspect': ['atmosphere', 'service'],
'position': [[10, 15], [10, 15]],
'sentiment': ['Positive', 'Negative'],
'probs': [[0.0002125321188941598, 0.0021749241277575493, 0.9976125955581665],
[0.9982984662055969, 0.0015329710440710187, 0.00016868062084540725]],
'confidence': [0.9976125955581665, 0.9982984662055969]},
{'sentence': 'i waited for 10 - 15 minutes for service ordered a beer & was never served again .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O'],
'tokens': ['i',
'waited',
'for',
'10',
'-',
'15',
'minutes',
'for',
'service',
'ordered',
'a',
'beer',
'&',
'was',
'never',
'served',
'again',
'.'],
'aspect': ['service', 'beer', 'served'],
'position': [[8, 11, 15], [8, 11, 15], [8, 11, 15]],
'sentiment': ['Negative', 'Neutral', 'Negative'],
'probs': [[0.9741093516349792, 0.02562684379518032, 0.00026382316718809307],
[0.023990344256162643, 0.9754378199577332, 0.0005718620959669352],
[0.7955166101455688, 0.2035738080739975, 0.0009095079149119556]],
'confidence': [0.9741093516349792, 0.9754378199577332, 0.7955166101455688]},
{'sentence': "i went home & looked them up online again where i discovered there is a link for a give away that does n ' t work so emailed the restaurant about the non existent service & deceptive link .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'went',
'home',
'&',
'looked',
'them',
'up',
'online',
'again',
'where',
'i',
'discovered',
'there',
'is',
'a',
'link',
'for',
'a',
'give',
'away',
'that',
'does',
'n',
"'",
't',
'work',
'so',
'emailed',
'the',
'restaurant',
'about',
'the',
'non',
'existent',
'service',
'&',
'deceptive',
'link',
'.'],
'aspect': ['service'],
'position': [[34]],
'sentiment': ['Negative'],
'probs': [[0.9985307455062866,
0.0012506459606811404,
0.0002185263583669439]],
'confidence': [0.9985307455062866]},
{'sentence': "after sitting at the bar for over 20 minutes the bar keep had made only 2 drinks & kept telling us she ' d be right with us .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['after',
'sitting',
'at',
'the',
'bar',
'for',
'over',
'20',
'minutes',
'the',
'bar',
'keep',
'had',
'made',
'only',
'2',
'drinks',
'&',
'kept',
'telling',
'us',
'she',
"'",
'd',
'be',
'right',
'with',
'us',
'.'],
'aspect': ['bar keep', 'drinks'],
'position': [[10, 11, 16], [10, 11, 16]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9980602860450745, 0.0008028776501305401, 0.0011368697742000222],
[0.0004916011239401996, 0.9990468621253967, 0.00046150540583766997]],
'confidence': [0.9980602860450745, 0.9990468621253967]},
{'sentence': 'we left without ever getting service .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['we', 'left', 'without', 'ever', 'getting', 'service', '.'],
'aspect': ['service'],
'position': [[5]],
'sentiment': ['Negative'],
'probs': [[0.9992552399635315,
0.00040694422204978764,
0.00033780100056901574]],
'confidence': [0.9992552399635315]},
{'sentence': 'best crab cakes in town',
'IOB': ['O', 'B-ASP', 'I-ASP', 'O', 'O'],
'tokens': ['best', 'crab', 'cakes', 'in', 'town'],
'aspect': ['crab cakes'],
'position': [[1, 2]],
'sentiment': ['Positive'],
'probs': [[0.00023994958610273898,
0.00024301803205162287,
0.9995169639587402]],
'confidence': [0.9995169639587402]},
{'sentence': " – that s a big statement considering i ' ve been pulling crab traps and making the cakes myself since i was about seven - but something about these little devils gets better every time .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'that',
's',
'a',
'big',
'statement',
'considering',
'i',
"'",
've',
'been',
'pulling',
'crab',
'traps',
'and',
'making',
'the',
'cakes',
'myself',
'since',
'i',
'was',
'about',
'seven',
'-',
'but',
'something',
'about',
'these',
'little',
'devils',
'gets',
'better',
'every',
'time',
'.'],
'aspect': ['pulling crab', 'the'],
'position': [[12, 13, 17, 36], [12, 13, 17, 36]],
'sentiment': ['Neutral', 'Neutral'],
'probs': [[0.0005767597467638552,
0.9989898800849915,
0.00043332105269655585],
[0.00042099066195078194, 0.9990450739860535, 0.0005339402123354375]],
'confidence': [0.9989898800849915, 0.9990450739860535]},
{'sentence': 'if you can , come to this place by boat and make it a whole evening .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['if',
'you',
'can',
',',
'come',
'to',
'this',
'place',
'by',
'boat',
'and',
'make',
'it',
'a',
'whole',
'evening',
'.'],
'aspect': ['place'],
'position': [[7]],
'sentiment': ['Negative'],
'probs': [[0.7725690007209778, 0.10850697755813599, 0.11892412602901459]],
'confidence': [0.7725690007209778]},
{'sentence': 'great seasonal fish and seafood , with a classy waterfront setting .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O'],
'tokens': ['great',
'seasonal',
'fish',
'and',
'seafood',
',',
'with',
'a',
'classy',
'waterfront',
'setting',
'.'],
'aspect': ['fish', 'seafood', 'waterfront setting'],
'position': [[2, 4, 9, 10], [2, 4, 9, 10], [2, 4, 9, 10]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00025401063612662256,
0.0003629018028732389,
0.9993830919265747],
[0.00015074043767526746, 0.0007267685141414404, 0.9991224408149719],
[0.00013036614109296352, 0.00047202190035022795, 0.9993976354598999]],
'confidence': [0.9993830919265747, 0.9991224408149719, 0.9993976354598999]},
{'sentence': 'great pizza , poor service',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP'],
'tokens': ['great', 'pizza', ',', 'poor', 'service'],
'aspect': ['pizza', 'service'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.002164541045203805, 0.0002584316534921527, 0.9975770115852356],
[0.024771125987172127, 0.0006762451957911253, 0.9745526313781738]],
'confidence': [0.9975770115852356, 0.9745526313781738]},
{'sentence': ' – love their pizza , especially the mushroom pizza .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'love',
'their',
'pizza',
',',
'especially',
'the',
'mushroom',
'pizza',
'.'],
'aspect': ['their', 'the mushroom'],
'position': [[3, 7, 8, 10], [3, 7, 8, 10]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00016740351566113532,
0.0004244167939759791,
0.9994082450866699],
[0.00019005082140211016, 0.0002437216608086601, 0.9995662569999695]],
'confidence': [0.9994082450866699, 0.9995662569999695]},
{'sentence': ' – love their pizza , especially the mushroom pizza .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'love',
'their',
'pizza',
',',
'especially',
'the',
'mushroom',
'pizza',
'.'],
'aspect': ['their', 'the mushroom'],
'position': [[3, 7, 8, 10], [3, 7, 8, 10]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00016740351566113532,
0.0004244167939759791,
0.9994082450866699],
[0.00019005082140211016, 0.0002437216608086601, 0.9995662569999695]],
'confidence': [0.9994082450866699, 0.9995662569999695]},
{'sentence': 'also love their caeser salad .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['also', 'love', 'their', 'caeser', 'salad', '.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': "prefer to order it and pick it up though because i do n ' t like the servers , one young woman in particular .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['prefer',
'to',
'order',
'it',
'and',
'pick',
'it',
'up',
'though',
'because',
'i',
'do',
'n',
"'",
't',
'like',
'the',
'servers',
',',
'one',
'young',
'woman',
'in',
'particular',
'.'],
'aspect': ['servers'],
'position': [[17]],
'sentiment': ['Negative'],
'probs': [[0.9991395473480225,
0.0006223462987691164,
0.00023805275850463659]],
'confidence': [0.9991395473480225]},
{'sentence': 'management should really take notice and train their waitstaff and teach them some proper manners .',
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['management',
'should',
'really',
'take',
'notice',
'and',
'train',
'their',
'waitstaff',
'and',
'teach',
'them',
'some',
'proper',
'manners',
'.'],
'aspect': ['management', 'waitstaff'],
'position': [[0, 8], [0, 8]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.6398630142211914, 0.3587345778942108, 0.001402354915626347],
[0.2353457659482956, 0.7642578482627869, 0.0003964038041885942]],
'confidence': [0.6398630142211914, 0.7642578482627869]},
{'sentence': "many people talk about the great pizza and poor service , so it ca n ' t just be the rantings of a few dissatisfied customers .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['many',
'people',
'talk',
'about',
'the',
'great',
'pizza',
'and',
'poor',
'service',
',',
'so',
'it',
'ca',
'n',
"'",
't',
'just',
'be',
'the',
'rantings',
'of',
'a',
'few',
'dissatisfied',
'customers',
'.'],
'aspect': ['pizza', 'service'],
'position': [[6, 9], [6, 9]],
'sentiment': ['Positive', 'Negative'],
'probs': [[0.13469719886779785, 0.0010822353651747108, 0.8642205595970154],
[0.990708589553833, 0.00579554308205843, 0.003495931625366211]],
'confidence': [0.8642205595970154, 0.990708589553833]},
{'sentence': "it ' s a great little place with tons of potential to be a neighborhood joint if the service were n ' t so impersonal and corporate - like .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['it',
"'",
's',
'a',
'great',
'little',
'place',
'with',
'tons',
'of',
'potential',
'to',
'be',
'a',
'neighborhood',
'joint',
'if',
'the',
'service',
'were',
'n',
"'",
't',
'so',
'impersonal',
'and',
'corporate',
'-',
'like',
'.'],
'aspect': ['place', 'service'],
'position': [[6, 18], [6, 18]],
'sentiment': ['Positive', 'Negative'],
'probs': [[0.0007537368801422417, 0.0002184194599976763, 0.9990278482437134],
[0.9869440793991089, 0.0008214370463974774, 0.01223450992256403]],
'confidence': [0.9990278482437134, 0.9869440793991089]},
{'sentence': 'great breakfast',
'IOB': ['O', 'B-ASP'],
'tokens': ['great', 'breakfast'],
'aspect': ['breakfast'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0005288032698445022,
0.00022995713516138494,
0.9992413520812988]],
'confidence': [0.9992413520812988]},
{'sentence': ' – this place is famous for their breakfast .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'B-ASP', 'O', '[SEP]'],
'tokens': [' ',
'–',
'this',
'place',
'is',
'famous',
'for',
'their',
'breakfast',
'.'],
'aspect': ['this', 'their'],
'position': [[2, 7, 9], [2, 7, 9]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00023674358089920133,
0.9982132911682129,
0.0015500038862228394],
[0.00017521853442303836, 0.0003840180579572916, 0.9994407296180725]],
'confidence': [0.9982132911682129, 0.9994407296180725]},
{'sentence': 'the food is great and they make a mean bloody mary .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'food',
'is',
'great',
'and',
'they',
'make',
'a',
'mean',
'bloody',
'mary',
'.'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.000171816092915833, 0.000505502917803824, 0.999322772026062]],
'confidence': [0.999322772026062]},
{'sentence': 'i love breakfast here .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['i', 'love', 'breakfast', 'here', '.'],
'aspect': ['breakfast'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00019242237613070756,
0.00032735144486650825,
0.9994803071022034]],
'confidence': [0.9994803071022034]},
{'sentence': 'their crab eggs benedict is addicting .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['their', 'crab', 'eggs', 'benedict', 'is', 'addicting', '.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'all their menu items are a hit , and they serve mimosas .',
'IOB': ['O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['all',
'their',
'menu',
'items',
'are',
'a',
'hit',
',',
'and',
'they',
'serve',
'mimosas',
'.'],
'aspect': ['menu items', 'mimosas'],
'position': [[2, 3, 11], [2, 3, 11]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.000253904378041625, 0.00023316667648032308, 0.9995129108428955],
[0.00022454642748925835, 0.9989516735076904, 0.0008237037109211087]],
'confidence': [0.9995129108428955, 0.9989516735076904]},
{'sentence': 'best chinese food i have tasted in a long time',
'IOB': ['O', 'B-ASP', 'I-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['best',
'chinese',
'food',
'i',
'have',
'tasted',
'in',
'a',
'long',
'time'],
'aspect': ['chinese food'],
'position': [[1, 2]],
'sentiment': ['Positive'],
'probs': [[0.00026529637398198247,
0.00022755474492441863,
0.9995070695877075]],
'confidence': [0.9995070695877075]},
{'sentence': 'the ambiance of the restaurant was nice and good for fine dinning .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'ambiance',
'of',
'the',
'restaurant',
'was',
'nice',
'and',
'good',
'for',
'fine',
'dinning',
'.'],
'aspect': ['ambiance', 'dinning'],
'position': [[1, 11], [1, 11]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00014256269787438214, 0.0005405180272646248, 0.999316930770874],
[0.00020418076019268483, 0.00034785535535775125, 0.9994478821754456]],
'confidence': [0.999316930770874, 0.9994478821754456]},
{'sentence': 'the staff was very nice and courteous and obviously chinese .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'staff',
'was',
'very',
'nice',
'and',
'courteous',
'and',
'obviously',
'chinese',
'.'],
'aspect': ['staff'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0002900036924984306,
0.00023848479031585157,
0.9994714856147766]],
'confidence': [0.9994714856147766]},
{'sentence': 'so about the prawns , they were fresh and had a slight crispiness about the batter . . . soooo good . . . the walnuts were cut in smaller pieces and very crunchy and tasty .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['so',
'about',
'the',
'prawns',
',',
'they',
'were',
'fresh',
'and',
'had',
'a',
'slight',
'crispiness',
'about',
'the',
'batter',
'.',
'.',
'.',
'soooo',
'good',
'.',
'.',
'.',
'the',
'walnuts',
'were',
'cut',
'in',
'smaller',
'pieces',
'and',
'very',
'crunchy',
'and',
'tasty',
'.'],
'aspect': ['prawns', 'walnuts'],
'position': [[3, 25], [3, 25]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0004602115077432245,
0.00025995541363954544,
0.9992799162864685],
[0.059707161039114, 0.0004035746678709984, 0.9398891925811768]],
'confidence': [0.9992799162864685, 0.9398891925811768]},
{'sentence': 'best honey walnyt prawns that we have every tasted .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['best',
'honey',
'walnyt',
'prawns',
'that',
'we',
'have',
'every',
'tasted',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'the brocollis were so fresh and tasty .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'brocollis', 'were', 'so', 'fresh', 'and', 'tasty', '.'],
'aspect': ['brocollis'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00025367995840497315,
0.00022775991237722337,
0.9995185136795044]],
'confidence': [0.9995185136795044]},
{'sentence': 'i would normally not finish the brocolli when i order these kinds of food but for the first time , every piece was as eventful as the first one . . . the scallops and prawns was so fresh and nicely cooked .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'would',
'normally',
'not',
'finish',
'the',
'brocolli',
'when',
'i',
'order',
'these',
'kinds',
'of',
'food',
'but',
'for',
'the',
'first',
'time',
',',
'every',
'piece',
'was',
'as',
'eventful',
'as',
'the',
'first',
'one',
'.',
'.',
'.',
'the',
'scallops',
'and',
'prawns',
'was',
'so',
'fresh',
'and',
'nicely',
'cooked',
'.'],
'aspect': ['food', 'scallops and prawns'],
'position': [[13, 33, 34, 35], [13, 33, 34, 35]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00034249149030074477,
0.9990034699440002,
0.0006541151087731123],
[0.0006024733884260058, 0.00017458060756325722, 0.9992228746414185]],
'confidence': [0.9990034699440002, 0.9992228746414185]},
{'sentence': 'for desert we had the mango ginger creme brulee . . . oh la la yummy ! ! !',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['for',
'desert',
'we',
'had',
'the',
'mango',
'ginger',
'creme',
'brulee',
'.',
'.',
'.',
'oh',
'la',
'la',
'yummy',
'!',
'!',
'!'],
'aspect': ['desert', 'brulee'],
'position': [[1, 8], [1, 8]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0002654230338521302, 0.999171257019043, 0.0005633487598970532],
[0.0012797127710655332, 0.00023182097356766462, 0.9984884262084961]],
'confidence': [0.999171257019043, 0.9984884262084961]},
{'sentence': 'we are for sure coming back to this restaurant .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['we',
'are',
'for',
'sure',
'coming',
'back',
'to',
'this',
'restaurant',
'.'],
'aspect': ['restaurant'],
'position': [[8]],
'sentiment': ['Positive'],
'probs': [[0.00040801550494506955,
0.0002063697320409119,
0.9993855953216553]],
'confidence': [0.9993855953216553]},
{'sentence': 'chintzy portions',
'IOB': ['O', 'B-ASP'],
'tokens': ['chintzy', 'portions'],
'aspect': ['portions'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.8043935894966125, 0.0010660981060937047, 0.19454027712345123]],
'confidence': [0.8043935894966125]},
{'sentence': ' – the sushi here is perfectly good , but for $ 5 a piece , either the slices of fish should be larger , or there should be no pretense that this is a moderately priced restaurant ( even for nyc ) .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'the',
'sushi',
'here',
'is',
'perfectly',
'good',
',',
'but',
'for',
'$',
'5',
'a',
'piece',
',',
'either',
'the',
'slices',
'of',
'fish',
'should',
'be',
'larger',
',',
'or',
'there',
'should',
'be',
'no',
'pretense',
'that',
'this',
'is',
'a',
'moderately',
'priced',
'restaurant',
'(',
'even',
'for',
'nyc',
')',
'.'],
'aspect': ['the', 'the slices of', 'moderately'],
'position': [[2, 17, 18, 19, 35, 43],
[2, 17, 18, 19, 35, 43],
[2, 17, 18, 19, 35, 43]],
'sentiment': ['Positive', 'Negative', 'Positive'],
'probs': [[0.00034893216798081994, 0.0036862879060208797, 0.995964765548706],
[0.9981480836868286, 0.0014469106681644917, 0.00040505340439267457],
[0.2989596128463745, 0.0011916962685063481, 0.6998486518859863]],
'confidence': [0.995964765548706, 0.9981480836868286, 0.6998486518859863]},
{'sentence': "i ' m astonished that this restaurant is categorized as $ $ $ rather than $ $ $ $ .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
"'",
'm',
'astonished',
'that',
'this',
'restaurant',
'is',
'categorized',
'as',
'$',
'$',
'$',
'rather',
'than',
'$',
'$',
'$',
'$',
'.'],
'aspect': ['as $ $'],
'position': [[9, 10, 11]],
'sentiment': ['Negative'],
'probs': [[0.9984416365623474,
0.0003543362545315176,
0.0012040719157084823]],
'confidence': [0.9984416365623474]},
{'sentence': 'terrible service , food ok , pricey',
'IOB': ['O', 'B-ASP', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['terrible', 'service', ',', 'food', 'ok', ',', 'pricey'],
'aspect': ['service', 'food'],
'position': [[1, 3], [1, 3]],
'sentiment': ['Negative', 'Positive'],
'probs': [[0.7353649139404297, 0.02881588786840439, 0.2358192354440689],
[0.10329385101795197, 0.1150679886341095, 0.7816380858421326]],
'confidence': [0.7353649139404297, 0.7816380858421326]},
{'sentence': "in other words , if they are n ' t making $ $ off of you then you do n ' t rate high on their ' service scale ' .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['in',
'other',
'words',
',',
'if',
'they',
'are',
'n',
"'",
't',
'making',
'$',
'$',
'off',
'of',
'you',
'then',
'you',
'do',
'n',
"'",
't',
'rate',
'high',
'on',
'their',
"'",
'service',
'scale',
"'",
'.'],
'aspect': ['service'],
'position': [[27]],
'sentiment': ['Negative'],
'probs': [[0.9261487722396851, 0.03097430057823658, 0.04287702217698097]],
'confidence': [0.9261487722396851]},
{'sentence': "food wise , its ok but a bit pricey for what you get considering the restaurant is n ' t a fancy place .",
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['food',
'wise',
',',
'its',
'ok',
'but',
'a',
'bit',
'pricey',
'for',
'what',
'you',
'get',
'considering',
'the',
'restaurant',
'is',
'n',
"'",
't',
'a',
'fancy',
'place',
'.'],
'aspect': ['food', 'place'],
'position': [[0, 22], [0, 22]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.2921079099178314, 0.7023361325263977, 0.005555951036512852],
[0.8833043575286865, 0.03995412960648537, 0.0767415389418602]],
'confidence': [0.7023361325263977, 0.8833043575286865]},
{'sentence': 'if i needed to name some they would include the location to the beach or golden gate park .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['if',
'i',
'needed',
'to',
'name',
'some',
'they',
'would',
'include',
'the',
'location',
'to',
'the',
'beach',
'or',
'golden',
'gate',
'park',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'another plus is the open feel of the restaurant with glass walls on all sides .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['another',
'plus',
'is',
'the',
'open',
'feel',
'of',
'the',
'restaurant',
'with',
'glass',
'walls',
'on',
'all',
'sides',
'.'],
'aspect': ['feel'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.00022875770810060203,
0.00024064310127869248,
0.999530553817749]],
'confidence': [0.999530553817749]},
{'sentence': 'amazing spanish mackeral special appetizer and perfect box sushi ( that eel with avodcao - - um um um ) .',
'IOB': ['O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['amazing',
'spanish',
'mackeral',
'special',
'appetizer',
'and',
'perfect',
'box',
'sushi',
'(',
'that',
'eel',
'with',
'avodcao',
'-',
'-',
'um',
'um',
'um',
')',
'.'],
'aspect': ['mackeral special appetizer', 'box sushi', 'eel with avodcao'],
'position': [[2, 3, 4, 7, 8, 11, 12, 13],
[2, 3, 4, 7, 8, 11, 12, 13],
[2, 3, 4, 7, 8, 11, 12, 13]],
'sentiment': ['Positive', 'Positive', 'Neutral'],
'probs': [[0.0005187783390283585, 0.0002476331719662994, 0.999233603477478],
[0.0004389494424685836, 0.0005289938417263329, 0.9990320205688477],
[0.0002865901624318212, 0.9009906053543091, 0.09872280806303024]],
'confidence': [0.999233603477478, 0.9990320205688477, 0.9009906053543091]},
{'sentence': "as usual the omikase did n ' t disappoint in freshness , although it scored low on creativity and selection .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O'],
'tokens': ['as',
'usual',
'the',
'omikase',
'did',
'n',
"'",
't',
'disappoint',
'in',
'freshness',
',',
'although',
'it',
'scored',
'low',
'on',
'creativity',
'and',
'selection',
'.'],
'aspect': ['creativity', 'selection'],
'position': [[17, 19], [17, 19]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9987288117408752,
0.0010940581560134888,
0.00017711763211991638],
[0.9984246492385864, 0.0014050821773707867, 0.00017034984193742275]],
'confidence': [0.9987288117408752, 0.9984246492385864]},
{'sentence': "their specialty rolls are impressive , though i ca n ' t remember what we had .",
'IOB': ['O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['their',
'specialty',
'rolls',
'are',
'impressive',
',',
'though',
'i',
'ca',
'n',
"'",
't',
'remember',
'what',
'we',
'had',
'.'],
'aspect': ['specialty rolls'],
'position': [[1, 2]],
'sentiment': ['Positive'],
'probs': [[0.0004970342852175236, 0.0014607389457523823, 0.998042106628418]],
'confidence': [0.998042106628418]},
{'sentence': 'great selection of sakes .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['great', 'selection', 'of', 'sakes', '.'],
'aspect': ['sakes'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.00025815953267738223,
0.00023507959849666804,
0.9995067119598389]],
'confidence': [0.9995067119598389]},
{'sentence': 'green tea creme brulee gets better each time i have it .',
'IOB': ['B-ASP', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['green',
'tea',
'creme',
'brulee',
'gets',
'better',
'each',
'time',
'i',
'have',
'it',
'.'],
'aspect': ['green', 'creme'],
'position': [[0, 2], [0, 2]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0006158739561215043, 0.002173804445192218, 0.9972103238105774],
[0.0003108018427155912, 0.001105426694266498, 0.9985837936401367]],
'confidence': [0.9972103238105774, 0.9985837936401367]},
{'sentence': "it is n ' t the cheapest sushi but has been worth it every time .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['it',
'is',
'n',
"'",
't',
'the',
'cheapest',
'sushi',
'but',
'has',
'been',
'worth',
'it',
'every',
'time',
'.'],
'aspect': ['sushi'],
'position': [[7]],
'sentiment': ['Negative'],
'probs': [[0.9785822033882141, 0.021147070452570915, 0.0002707254607230425]],
'confidence': [0.9785822033882141]},
{'sentence': 'very poor customer service .',
'IOB': ['O', 'O', 'B-ASP', 'I-ASP', 'O'],
'tokens': ['very', 'poor', 'customer', 'service', '.'],
'aspect': ['customer service'],
'position': [[2, 3]],
'sentiment': ['Negative'],
'probs': [[0.9994204044342041,
0.00033956943661905825,
0.00024007448519114405]],
'confidence': [0.9994204044342041]},
{'sentence': " – schooner or later ' s charming location along the marina in long beach and average food does not , unfortunately , compensate for its very poor customer service .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'schooner',
'or',
'later',
"'",
's',
'charming',
'location',
'along',
'the',
'marina',
'in',
'long',
'beach',
'and',
'average',
'food',
'does',
'not',
',',
'unfortunately',
',',
'compensate',
'for',
'its',
'very',
'poor',
'customer',
'service',
'.'],
'aspect': ['charming', 'average', 'customer'],
'position': [[7, 16, 28, 30], [7, 16, 28, 30], [7, 16, 28, 30]],
'sentiment': ['Positive', 'Neutral', 'Negative'],
'probs': [[0.0003079298185184598, 0.0010067732073366642, 0.9986851811408997],
[0.01627238281071186, 0.9809998273849487, 0.002727797022089362],
[0.9799757599830627, 0.019870983436703682, 0.00015327548317145556]],
'confidence': [0.9986851811408997, 0.9809998273849487, 0.9799757599830627]},
{'sentence': 'while this diner had reasonably good food , the restaurant staff seemed completely indifferent to our presence , and this attitude was reflected in the lack of service .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['while',
'this',
'diner',
'had',
'reasonably',
'good',
'food',
',',
'the',
'restaurant',
'staff',
'seemed',
'completely',
'indifferent',
'to',
'our',
'presence',
',',
'and',
'this',
'attitude',
'was',
'reflected',
'in',
'the',
'lack',
'of',
'service',
'.'],
'aspect': ['diner', 'food', 'staff', 'service'],
'position': [[2, 6, 10, 27], [2, 6, 10, 27], [2, 6, 10, 27], [2, 6, 10, 27]],
'sentiment': ['Neutral', 'Negative', 'Negative', 'Negative'],
'probs': [[0.0002438394003547728, 0.9978779554367065, 0.0018781953258439898],
[0.7287617921829224, 0.07128125429153442, 0.1999569833278656],
[0.9989068508148193, 0.0008398532518185675, 0.0002533200313337147],
[0.995307981967926, 0.004516050685197115, 0.0001759962906362489]],
'confidence': [0.9978779554367065,
0.7287617921829224,
0.9989068508148193,
0.995307981967926]},
{'sentence': 'after one member of our party had been bumped repeatedly by a waitress , a polite request that he not be bumped sent the waitress into an abusive rant .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['after',
'one',
'member',
'of',
'our',
'party',
'had',
'been',
'bumped',
'repeatedly',
'by',
'a',
'waitress',
',',
'a',
'polite',
'request',
'that',
'he',
'not',
'be',
'bumped',
'sent',
'the',
'waitress',
'into',
'an',
'abusive',
'rant',
'.'],
'aspect': ['waitress'],
'position': [[12]],
'sentiment': ['Negative'],
'probs': [[0.8158661127090454, 0.1831592619419098, 0.0009746045689098537]],
'confidence': [0.8158661127090454]},
{'sentence': 'a brief conversation with the manager at the end of the meal was the greatest disappointment - - to say we had been " blown off " would be an understatement .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['a',
'brief',
'conversation',
'with',
'the',
'manager',
'at',
'the',
'end',
'of',
'the',
'meal',
'was',
'the',
'greatest',
'disappointment',
'-',
'-',
'to',
'say',
'we',
'had',
'been',
'"',
'blown',
'off',
'"',
'would',
'be',
'an',
'understatement',
'.'],
'aspect': ['manager', 'meal'],
'position': [[5, 11], [5, 11]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9993489384651184, 0.0003317254886496812, 0.0003192601434420794],
[0.00038634464726783335, 0.9989964365959167, 0.0006172677967697382]],
'confidence': [0.9993489384651184, 0.9989964365959167]},
{'sentence': 'the manager continually interrupted with " is there anything else i can do for you ? " , a strange comment because she had hardly listened , let alone responded to our expression of disappointment at our experience .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'manager',
'continually',
'interrupted',
'with',
'"',
'is',
'there',
'anything',
'else',
'i',
'can',
'do',
'for',
'you',
'?',
'"',
',',
'a',
'strange',
'comment',
'because',
'she',
'had',
'hardly',
'listened',
',',
'let',
'alone',
'responded',
'to',
'our',
'expression',
'of',
'disappointment',
'at',
'our',
'experience',
'.'],
'aspect': ['manager'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.9970859885215759,
0.0020415429025888443,
0.0008724051294848323]],
'confidence': [0.9970859885215759]},
{'sentence': 'you are with a hot date and he / she has an urge for sushi . . . then this might be the place .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['you',
'are',
'with',
'a',
'hot',
'date',
'and',
'he',
'/',
'she',
'has',
'an',
'urge',
'for',
'sushi',
'.',
'.',
'.',
'then',
'this',
'might',
'be',
'the',
'place',
'.'],
'aspect': ['sushi'],
'position': [[14]],
'sentiment': ['Neutral'],
'probs': [[0.000562975590582937, 0.6490190625190735, 0.35041797161102295]],
'confidence': [0.6490190625190735]},
{'sentence': 'the fish was fresh , though it was cut very thin .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'fish',
'was',
'fresh',
',',
'though',
'it',
'was',
'cut',
'very',
'thin',
'.'],
'aspect': ['fish'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00029802892822772264,
0.00029831440770067275,
0.9994035959243774]],
'confidence': [0.9994035959243774]},
{'sentence': 'great service .',
'IOB': ['O', 'B-ASP', 'O'],
'tokens': ['great', 'service', '.'],
'aspect': ['service'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0006838664412498474,
0.0002264921204186976,
0.9990895986557007]],
'confidence': [0.9990895986557007]},
{'sentence': 'good sake selection .',
'IOB': ['O', 'B-ASP', 'O', 'O'],
'tokens': ['good', 'sake', 'selection', '.'],
'aspect': ['sake'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00017202804156113416,
0.0014705422800034285,
0.9983574748039246]],
'confidence': [0.9983574748039246]},
{'sentence': 'dungeness crabs here !',
'IOB': ['O', 'O', 'O', 'O'],
'tokens': ['dungeness', 'crabs', 'here', '!'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': " – ray ' s is the place to go for high quality seafood dinners .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'ray',
"'",
's',
'is',
'the',
'place',
'to',
'go',
'for',
'high',
'quality',
'seafood',
'dinners',
'.'],
'aspect': ['quality seafood'],
'position': [[12, 13, 15]],
'sentiment': ['Positive'],
'probs': [[0.0001904923701658845,
0.00023225929180625826,
0.9995772242546082]],
'confidence': [0.9995772242546082]},
{'sentence': "we were only in seattle for one night and i ' m so glad we picked rays for dinner !",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['we',
'were',
'only',
'in',
'seattle',
'for',
'one',
'night',
'and',
'i',
"'",
'm',
'so',
'glad',
'we',
'picked',
'rays',
'for',
'dinner',
'!'],
'aspect': ['dinner'],
'position': [[18]],
'sentiment': ['Neutral'],
'probs': [[0.0004185705038253218, 0.9488168358802795, 0.05076466500759125]],
'confidence': [0.9488168358802795]},
{'sentence': "i love dungeness crabs and at ray ' s you can get them served in about 6 different ways !",
'IOB': ['O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'love',
'dungeness',
'crabs',
'and',
'at',
'ray',
"'",
's',
'you',
'can',
'get',
'them',
'served',
'in',
'about',
'6',
'different',
'ways',
'!'],
'aspect': ['dungeness crabs', 'served'],
'position': [[2, 3, 13], [2, 3, 13]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0003589789557736367, 0.0004823909839615226, 0.9991586208343506],
[0.0004477543698158115, 0.03435751050710678, 0.9651947617530823]],
'confidence': [0.9991586208343506, 0.9651947617530823]},
{'sentence': 'we shared the family platter and i especially enjoyed the black cod in sake kasu .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['we',
'shared',
'the',
'family',
'platter',
'and',
'i',
'especially',
'enjoyed',
'the',
'black',
'cod',
'in',
'sake',
'kasu',
'.'],
'aspect': ['family platter', 'black'],
'position': [[3, 4, 10], [3, 4, 10]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00022490952687803656,
0.9991968274116516,
0.0005782278021797538],
[0.0002799954963847995, 0.0048209973610937595, 0.9948989748954773]],
'confidence': [0.9991968274116516, 0.9948989748954773]},
{'sentence': 'i ended the meal with the unusual dessert of a port and chocolate tasting . . . . yummy !',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'ended',
'the',
'meal',
'with',
'the',
'unusual',
'dessert',
'of',
'a',
'port',
'and',
'chocolate',
'tasting',
'.',
'.',
'.',
'.',
'yummy',
'!'],
'aspect': ['meal', 'dessert', 'port'],
'position': [[3, 7, 10], [3, 7, 10], [3, 7, 10]],
'sentiment': ['Neutral', 'Positive', 'Neutral'],
'probs': [[0.0003470777883194387, 0.9988675117492676, 0.0007854767027311027],
[0.0010803635232150555, 0.39266541600227356, 0.6062542200088501],
[0.0008847728022374213, 0.649896502494812, 0.3492187559604645]],
'confidence': [0.9988675117492676, 0.6062542200088501, 0.649896502494812]},
{'sentence': 'and the service was simply spendid - quite a delight .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['and',
'the',
'service',
'was',
'simply',
'spendid',
'-',
'quite',
'a',
'delight',
'.'],
'aspect': ['service'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.000393474503653124,
0.00022306415485218167,
0.9993834495544434]],
'confidence': [0.9993834495544434]},
{'sentence': ' – great drinks , corn beef hash , coffee , b fast burritos , gluten free menu .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'great',
'drinks',
',',
'corn',
'beef',
'hash',
',',
'coffee',
',',
'b',
'fast',
'burritos',
',',
'gluten',
'free',
'menu',
'.'],
'aspect': ['great', ', corn beef', ','],
'position': [[2, 4, 5, 6, 8, 18], [2, 4, 5, 6, 8, 18], [2, 4, 5, 6, 8, 18]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.0005791216972284019,
0.00026113292551599443,
0.9991598129272461],
[0.0002137110714102164, 0.0009622338693588972, 0.9988240599632263],
[0.0004273058148100972, 0.00047599090612493455, 0.9990966320037842]],
'confidence': [0.9991598129272461, 0.9988240599632263, 0.9990966320037842]},
{'sentence': 'the service is fantastic at this fun place .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['the',
'service',
'is',
'fantastic',
'at',
'this',
'fun',
'place',
'.'],
'aspect': ['service', 'place'],
'position': [[1, 7], [1, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002518929832149297,
0.00026819034246727824,
0.9994799494743347],
[0.0002489167090971023, 0.00024015552480705082, 0.9995108842849731]],
'confidence': [0.9994799494743347, 0.9995108842849731]},
{'sentence': 'if there is a line very day of the week for the entire time a place is open , you know it is great .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['if',
'there',
'is',
'a',
'line',
'very',
'day',
'of',
'the',
'week',
'for',
'the',
'entire',
'time',
'a',
'place',
'is',
'open',
',',
'you',
'know',
'it',
'is',
'great',
'.'],
'aspect': ['place'],
'position': [[15]],
'sentiment': ['Positive'],
'probs': [[0.00024616660084575415, 0.1479644477367401, 0.8517894148826599]],
'confidence': [0.8517894148826599]},
{'sentence': 'best neighborhood standby .',
'IOB': ['O', 'O', 'O', 'O'],
'tokens': ['best', 'neighborhood', 'standby', '.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': 'in grammercy / union square / east village this is my neighbors and my favorite spot .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['in',
'grammercy',
'/',
'union',
'square',
'/',
'east',
'village',
'this',
'is',
'my',
'neighbors',
'and',
'my',
'favorite',
'spot',
'.'],
'aspect': ['spot'],
'position': [[15]],
'sentiment': ['Positive'],
'probs': [[0.0002735460293479264,
0.00023091699404176325,
0.9994955062866211]],
'confidence': [0.9994955062866211]},
{'sentence': 'the music is great , no night better or worse , the bar tenders are generous with the pouring , and the lighthearted atmosphere will lifts you spirits .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'music',
'is',
'great',
',',
'no',
'night',
'better',
'or',
'worse',
',',
'the',
'bar',
'tenders',
'are',
'generous',
'with',
'the',
'pouring',
',',
'and',
'the',
'lighthearted',
'atmosphere',
'will',
'lifts',
'you',
'spirits',
'.'],
'aspect': ['music', 'bar tenders', 'atmosphere'],
'position': [[1, 12, 13, 23], [1, 12, 13, 23], [1, 12, 13, 23]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00048069667536765337,
0.0002696687588468194,
0.9992496371269226],
[0.0003351722261868417, 0.4050664007663727, 0.5945984721183777],
[0.0001211718627018854, 0.001835459377616644, 0.998043417930603]],
'confidence': [0.9992496371269226, 0.5945984721183777, 0.998043417930603]},
{'sentence': 'oh , and the cheese fries are awesome !',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'I-ASP', 'O', 'O', 'O'],
'tokens': ['oh',
',',
'and',
'the',
'cheese',
'fries',
'are',
'awesome',
'!'],
'aspect': ['cheese fries'],
'position': [[4, 5]],
'sentiment': ['Positive'],
'probs': [[0.00016600826347712427,
0.00030009972397238016,
0.9995338916778564]],
'confidence': [0.9995338916778564]},
{'sentence': 'good food , great service , average prices ( for the strip )',
'IOB': ['O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['good',
'food',
',',
'great',
'service',
',',
'average',
'prices',
'(',
'for',
'the',
'strip',
')'],
'aspect': ['food', 'service', 'prices'],
'position': [[1, 4, 7], [1, 4, 7], [1, 4, 7]],
'sentiment': ['Positive', 'Positive', 'Neutral'],
'probs': [[0.0009969257516786456,
0.00021823162387590855,
0.9987848401069641],
[0.0005903248093090951, 0.00034126691753044724, 0.9990684390068054],
[0.0007231944473460317, 0.9738725423812866, 0.025404274463653564]],
'confidence': [0.9987848401069641, 0.9990684390068054, 0.9738725423812866]},
{'sentence': ' – i decided to eat at stack because of their price fixed pre - show dinner .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'decided',
'to',
'eat',
'at',
'stack',
'because',
'of',
'their',
'price',
'fixed',
'pre',
'-',
'show',
'dinner',
'.'],
'aspect': ['their', '- show'],
'position': [[10, 14, 15, 17], [10, 14, 15, 17]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00116926955524832, 0.23091302812099457, 0.7679176330566406],
[0.0006075708661228418, 0.4543690085411072, 0.5450234413146973]],
'confidence': [0.7679176330566406, 0.5450234413146973]},
{'sentence': 'when i walked in , i was taken aback by their incredible wood decor .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O'],
'tokens': ['when',
'i',
'walked',
'in',
',',
'i',
'was',
'taken',
'aback',
'by',
'their',
'incredible',
'wood',
'decor',
'.'],
'aspect': ['wood decor'],
'position': [[12, 13]],
'sentiment': ['Positive'],
'probs': [[0.00021867037867195904,
0.00023027884890325367,
0.999550998210907]],
'confidence': [0.999550998210907]},
{'sentence': 'the music playing was very hip , 20 - 30 something pop music , but the subwoofer to the sound system was located under my seat , which became annoying midway through dinner .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'music',
'playing',
'was',
'very',
'hip',
',',
'20',
'-',
'30',
'something',
'pop',
'music',
',',
'but',
'the',
'subwoofer',
'to',
'the',
'sound',
'system',
'was',
'located',
'under',
'my',
'seat',
',',
'which',
'became',
'annoying',
'midway',
'through',
'dinner',
'.'],
'aspect': ['subwoofer', 'dinner'],
'position': [[16, 32], [16, 32]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9829923510551453, 0.00330526870675385, 0.013702388852834702],
[0.011240571737289429, 0.9884418845176697, 0.0003175738675054163]],
'confidence': [0.9829923510551453, 0.9884418845176697]},
{'sentence': 'i got the shellfish and shrimp appetizer and it was alright .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['i',
'got',
'the',
'shellfish',
'and',
'shrimp',
'appetizer',
'and',
'it',
'was',
'alright',
'.'],
'aspect': ['shrimp'],
'position': [[5]],
'sentiment': ['Neutral'],
'probs': [[0.006914654280990362, 0.9662073254585266, 0.026878051459789276]],
'confidence': [0.9662073254585266]},
{'sentence': "it was n ' t the freshest seafood ever , but the taste and presentation was ok .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['it',
'was',
'n',
"'",
't',
'the',
'freshest',
'seafood',
'ever',
',',
'but',
'the',
'taste',
'and',
'presentation',
'was',
'ok',
'.'],
'aspect': ['seafood', 'taste'],
'position': [[7, 12], [7, 12]],
'sentiment': ['Negative', 'Positive'],
'probs': [[0.9989809393882751,
0.0008275953005068004,
0.00019148144929204136],
[0.00030601219623349607, 0.03742898628115654, 0.9622649550437927]],
'confidence': [0.9989809393882751, 0.9622649550437927]},
{'sentence': 'i picked the asparagus , which turned out to be incredible and perfectly prepared .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'picked',
'the',
'asparagus',
',',
'which',
'turned',
'out',
'to',
'be',
'incredible',
'and',
'perfectly',
'prepared',
'.'],
'aspect': ['asparagus'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.0003170702839270234, 0.028106635436415672, 0.9715762734413147]],
'confidence': [0.9715762734413147]},
{'sentence': 'the 9 oz steak came next and it tasted great , at least initially .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'9',
'oz',
'steak',
'came',
'next',
'and',
'it',
'tasted',
'great',
',',
'at',
'least',
'initially',
'.'],
'aspect': ['steak'],
'position': [[3]],
'sentiment': ['Positive'],
'probs': [[0.0006663997191935778, 0.1504162698984146, 0.8489173054695129]],
'confidence': [0.8489173054695129]},
{'sentence': 'the steak was done to my exact liking ( medium rare ) and was nice and juicy .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'steak',
'was',
'done',
'to',
'my',
'exact',
'liking',
'(',
'medium',
'rare',
')',
'and',
'was',
'nice',
'and',
'juicy',
'.'],
'aspect': ['steak'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00025527161778882146,
0.00031154477619566023,
0.9994331002235413]],
'confidence': [0.9994331002235413]},
{'sentence': 'it ? s served with either a peppercorn sauce or red wine reduction , though both were indistinguishable in taste .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['it',
'?',
's',
'served',
'with',
'either',
'a',
'peppercorn',
'sauce',
'or',
'red',
'wine',
'reduction',
',',
'though',
'both',
'were',
'indistinguishable',
'in',
'taste',
'.'],
'aspect': ['served', 'red wine reduction', 'taste'],
'position': [[3, 10, 11, 12, 19], [3, 10, 11, 12, 19], [3, 10, 11, 12, 19]],
'sentiment': ['Neutral', 'Neutral', 'Negative'],
'probs': [[0.17780701816082, 0.8216696381568909, 0.0005232970579527318],
[0.004411044530570507, 0.9952604174613953, 0.0003285867569502443],
[0.7206714153289795, 0.014185847714543343, 0.2651427388191223]],
'confidence': [0.8216696381568909, 0.9952604174613953, 0.7206714153289795]},
{'sentence': 'though , one thing i realized later on was that the restaurant either used msg or a meat tenderizer on the steak .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['though',
',',
'one',
'thing',
'i',
'realized',
'later',
'on',
'was',
'that',
'the',
'restaurant',
'either',
'used',
'msg',
'or',
'a',
'meat',
'tenderizer',
'on',
'the',
'steak',
'.'],
'aspect': ['msg', 'meat tenderizer', 'steak'],
'position': [[14, 17, 18, 21], [14, 17, 18, 21], [14, 17, 18, 21]],
'sentiment': ['Negative', 'Neutral', 'Neutral'],
'probs': [[0.7709355354309082, 0.22875607013702393, 0.00030838607926853],
[0.06232401356101036, 0.9373965263366699, 0.00027946443879045546],
[0.0007550634909421206, 0.9986067414283752, 0.0006382704013958573]],
'confidence': [0.7709355354309082, 0.9373965263366699, 0.9986067414283752]},
{'sentence': 'the desert was the perfect ending to an almost perfect dinner .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['the',
'desert',
'was',
'the',
'perfect',
'ending',
'to',
'an',
'almost',
'perfect',
'dinner',
'.'],
'aspect': ['desert', 'dinner'],
'position': [[1, 10], [1, 10]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0007359617156907916, 0.0003625081153586507, 0.9989016056060791],
[0.0014536972157657146, 0.00753840571269393, 0.9910078644752502]],
'confidence': [0.9989016056060791, 0.9910078644752502]},
{'sentence': 'but the servers were extremely attentive and very friendly .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['but',
'the',
'servers',
'were',
'extremely',
'attentive',
'and',
'very',
'friendly',
'.'],
'aspect': ['servers'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00023649721697438508,
0.00025257820379920304,
0.9995108842849731]],
'confidence': [0.9995108842849731]},
{'sentence': 'overall , i would go back and eat at the restaurant again .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['overall',
',',
'i',
'would',
'go',
'back',
'and',
'eat',
'at',
'the',
'restaurant',
'again',
'.'],
'aspect': [],
'position': [],
'sentiment': [],
'probs': [],
'confidence': []},
{'sentence': "good sake , good food – i honestly do n ' t know much about japanese food at all .",
'IOB': ['O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['good',
'sake',
',',
'good',
'food',
'–',
'i',
'honestly',
'do',
'n',
"'",
't',
'know',
'much',
'about',
'japanese',
'food',
'at',
'all',
'.'],
'aspect': ['sake', 'food'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0011114648077636957, 0.00021621078485623002, 0.998672366142273],
[0.000649010471533984, 0.0002738263865467161, 0.9990772008895874]],
'confidence': [0.998672366142273, 0.9990772008895874]},
{'sentence': 'server made several sake suggestions which were very good .',
'IOB': ['B-ASP', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['server',
'made',
'several',
'sake',
'suggestions',
'which',
'were',
'very',
'good',
'.'],
'aspect': ['server', 'sake'],
'position': [[0, 3], [0, 3]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0005365253309719265, 0.4667348265647888, 0.5327286720275879],
[0.00040993947186507285, 0.009515549056231976, 0.9900745749473572]],
'confidence': [0.5327286720275879, 0.9900745749473572]},
{'sentence': 'had many dishes but the best was the lobster 3 ways .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['had',
'many',
'dishes',
'but',
'the',
'best',
'was',
'the',
'lobster',
'3',
'ways',
'.'],
'aspect': ['dishes', 'lobster'],
'position': [[2, 8], [2, 8]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0003969772660639137, 0.9860149621963501, 0.013588021509349346],
[0.0004152768524363637, 0.000400106655433774, 0.9991846680641174]],
'confidence': [0.9860149621963501, 0.9991846680641174]},
{'sentence': 'the waiter was a bit unfriendly and the feel of the restaurant was crowded .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'waiter',
'was',
'a',
'bit',
'unfriendly',
'and',
'the',
'feel',
'of',
'the',
'restaurant',
'was',
'crowded',
'.'],
'aspect': ['waiter'],
'position': [[1]],
'sentiment': ['Negative'],
'probs': [[0.9976882934570312,
0.0020995803643018007,
0.0002121865254594013]],
'confidence': [0.9976882934570312]},
{'sentence': 'also , there was only one bathroom stall - probably need more for such big crowds .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['also',
',',
'there',
'was',
'only',
'one',
'bathroom',
'stall',
'-',
'probably',
'need',
'more',
'for',
'such',
'big',
'crowds',
'.'],
'aspect': ['bathroom stall', 'crowds'],
'position': [[6, 7, 15], [6, 7, 15]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.4623614549636841, 0.5369933247566223, 0.0006451836670748889],
[0.9956133365631104, 0.0033473740331828594, 0.0010391599498689175]],
'confidence': [0.5369933247566223, 0.9956133365631104]},
{'sentence': 'most importantly , we were so excited about the food after seeing the very creative menu .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['most',
'importantly',
',',
'we',
'were',
'so',
'excited',
'about',
'the',
'food',
'after',
'seeing',
'the',
'very',
'creative',
'menu',
'.'],
'aspect': ['food', 'menu'],
'position': [[9, 15], [9, 15]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00024124591436702758, 0.9617336988449097, 0.03802507370710373],
[0.00047686550533398986, 0.00021309545263648033, 0.9993100166320801]],
'confidence': [0.9617336988449097, 0.9993100166320801]},
{'sentence': 'at best , the food was good and definately overpriced .',
'IOB': ['O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['at',
'best',
',',
'the',
'food',
'was',
'good',
'and',
'definately',
'overpriced',
'.'],
'aspect': ['food'],
'position': [[4]],
'sentiment': ['Positive'],
'probs': [[0.007437530439347029, 0.005340395029634237, 0.9872221350669861]],
'confidence': [0.9872221350669861]},
{'sentence': 'for the amount of food we got the prices should have been lower .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['for',
'the',
'amount',
'of',
'food',
'we',
'got',
'the',
'prices',
'should',
'have',
'been',
'lower',
'.'],
'aspect': ['food', 'prices'],
'position': [[4, 8], [4, 8]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.00032208539778366685, 0.5953931212425232, 0.4042847454547882],
[0.99856036901474, 0.0003132479905616492, 0.0011262836633250117]],
'confidence': [0.5953931212425232, 0.99856036901474]},
{'sentence': 'my favortie pizza joint in seattle',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['my', 'favortie', 'pizza', 'joint', 'in', 'seattle'],
'aspect': ['pizza'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.0001959782384801656,
0.00031011883402243257,
0.9994938373565674]],
'confidence': [0.9994938373565674]},
{'sentence': ' – this is my " must bring out of town guests to " restaurant and they always enjoy and rave about it .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'this',
'is',
'my',
'"',
'must',
'bring',
'out',
'of',
'town',
'guests',
'to',
'"',
'restaurant',
'and',
'they',
'always',
'enjoy',
'and',
'rave',
'about',
'it',
'.'],
'aspect': ['"'],
'position': [[13, 23]],
'sentiment': ['Positive'],
'probs': [[0.0002050126058747992,
0.0009499071747995913,
0.9988449811935425]],
'confidence': [0.9988449811935425]},
{'sentence': 'the pizza is delicious and the salads are fantastic .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the',
'pizza',
'is',
'delicious',
'and',
'the',
'salads',
'are',
'fantastic',
'.'],
'aspect': ['pizza', 'salads'],
'position': [[1, 6], [1, 6]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00024093143292702734,
0.00024415069492533803,
0.9995149374008179],
[0.00021327391732484102, 0.0002625190536491573, 0.9995242357254028]],
'confidence': [0.9995149374008179, 0.9995242357254028]},
{'sentence': "i ' ve always found the wait staff and , if you sit at the bar , the cooks very friendly .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['i',
"'",
've',
'always',
'found',
'the',
'wait',
'staff',
'and',
',',
'if',
'you',
'sit',
'at',
'the',
'bar',
',',
'the',
'cooks',
'very',
'friendly',
'.'],
'aspect': ['wait staff', 'bar', 'cooks'],
'position': [[6, 7, 15, 18], [6, 7, 15, 18], [6, 7, 15, 18]],
'sentiment': ['Positive', 'Neutral', 'Positive'],
'probs': [[0.001021487289108336, 0.12993812561035156, 0.8690404295921326],
[0.00024652673164382577, 0.9980446100234985, 0.0017088050954043865],
[0.0011448159348219633, 0.00025036107399500906, 0.9986048340797424]],
'confidence': [0.8690404295921326, 0.9980446100234985, 0.9986048340797424]},
{'sentence': 'i also really enjoy the simplicity of the decor and intimate feeling of a small restaurant .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'also',
'really',
'enjoy',
'the',
'simplicity',
'of',
'the',
'decor',
'and',
'intimate',
'feeling',
'of',
'a',
'small',
'restaurant',
'.'],
'aspect': ['decor'],
'position': [[8]],
'sentiment': ['Positive'],
'probs': [[0.00015583432104904205,
0.0009851751383394003,
0.9988589286804199]],
'confidence': [0.9988589286804199]},
{'sentence': ' – my husband and i love eating at mioposto caf é .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'my',
'husband',
'and',
'i',
'love',
'eating',
'at',
'mioposto',
'caf',
'é',
'.'],
'aspect': ['love'],
'position': [[6, 12]],
'sentiment': ['Positive'],
'probs': [[0.00014836722402833402,
0.0006078816950321198,
0.9992437362670898]],
'confidence': [0.9992437362670898]},
{'sentence': 'we ’ re ca n ’ t say enough about their delicious gourmet pizza ’ s !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O'],
'tokens': ['we',
'’',
're',
'ca',
'n',
'’',
't',
'say',
'enough',
'about',
'their',
'delicious',
'gourmet',
'pizza',
'’',
's',
'!'],
'aspect': ['gourmet pizza'],
'position': [[12, 13]],
'sentiment': ['Positive'],
'probs': [[0.0002055301156360656,
0.00027339105145074427,
0.9995211362838745]],
'confidence': [0.9995211362838745]},
{'sentence': 'you wo n ’ t be disappointed by their menu .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['you',
'wo',
'n',
'’',
't',
'be',
'disappointed',
'by',
'their',
'menu',
'.'],
'aspect': ['menu'],
'position': [[9]],
'sentiment': ['Positive'],
'probs': [[0.00027709323330782354, 0.03750940412282944, 0.9622135162353516]],
'confidence': [0.9622135162353516]},
{'sentence': 'the pizza ’ s are thin crust and the menu offers very creative combinations and toppings .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'pizza',
'’',
's',
'are',
'thin',
'crust',
'and',
'the',
'menu',
'offers',
'very',
'creative',
'combinations',
'and',
'toppings',
'.'],
'aspect': ['pizza', 'crust', 'menu', 'toppings'],
'position': [[1, 6, 9, 15], [1, 6, 9, 15], [1, 6, 9, 15], [1, 6, 9, 15]],
'sentiment': ['Positive', 'Positive', 'Neutral', 'Positive'],
'probs': [[0.0021043044980615377, 0.0035773429553955793, 0.994318425655365],
[0.0015492242528125644, 0.047497957944869995, 0.9509528279304504],
[0.0004207919118925929, 0.8046694397926331, 0.19490978121757507],
[0.0004803965275641531, 0.005101173650473356, 0.9944185018539429]],
'confidence': [0.994318425655365,
0.9509528279304504,
0.8046694397926331,
0.9944185018539429]},
{'sentence': 'the pizza ’ s are light and scrumptious .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'pizza',
'’',
's',
'are',
'light',
'and',
'scrumptious',
'.'],
'aspect': ['pizza'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00086876010755077, 0.00042861324618570507, 0.9987026453018188]],
'confidence': [0.9987026453018188]},
{'sentence': 'try the pizza ensalata !',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['try', 'the', 'pizza', 'ensalata', '!'],
'aspect': ['pizza'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00037331177736632526, 0.13279883563518524, 0.8668277859687805]],
'confidence': [0.8668277859687805]},
{'sentence': 'the pizza ’ s are not huge and the crust is thin … keep that in mind when you ’ re ordering .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'pizza',
'’',
's',
'are',
'not',
'huge',
'and',
'the',
'crust',
'is',
'thin',
'…',
'keep',
'that',
'in',
'mind',
'when',
'you',
'’',
're',
'ordering',
'.'],
'aspect': ['pizza', 'crust'],
'position': [[1, 9], [1, 9]],
'sentiment': ['Negative', 'Positive'],
'probs': [[0.9341416358947754, 0.06473517417907715, 0.0011231822427362204],
[0.0003405797469895333, 0.0009086640784516931, 0.9987506866455078]],
'confidence': [0.9341416358947754, 0.9987506866455078]},
{'sentence': 'the food is sinful .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the', 'food', 'is', 'sinful', '.'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0001781759347068146,
0.0003397386462893337,
0.9994822144508362]],
'confidence': [0.9994822144508362]},
{'sentence': 'the staff was really friendly .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'staff', 'was', 'really', 'friendly', '.'],
'aspect': ['staff'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00029818524490110576,
0.00026784115470945835,
0.9994339346885681]],
'confidence': [0.9994339346885681]},
{'sentence': 'the atmosphere was great .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['the', 'atmosphere', 'was', 'great', '.'],
'aspect': ['atmosphere'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00017021861276589334,
0.00034191165468655527,
0.9994877576828003]],
'confidence': [0.9994877576828003]},
{'sentence': "the specialty here is decadent pancakes , but i ' ve been back now four times , and i ' ve been wowed every time .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'specialty',
'here',
'is',
'decadent',
'pancakes',
',',
'but',
'i',
"'",
've',
'been',
'back',
'now',
'four',
'times',
',',
'and',
'i',
"'",
've',
'been',
'wowed',
'every',
'time',
'.'],
'aspect': ['pancakes'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.00021394784562289715,
0.021478595212101936,
0.9783073663711548]],
'confidence': [0.9783073663711548]},
{'sentence': 'nothing on the menu is less than amazing .',
'IOB': ['O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['nothing',
'on',
'the',
'menu',
'is',
'less',
'than',
'amazing',
'.'],
'aspect': ['menu'],
'position': [[3]],
'sentiment': ['Negative'],
'probs': [[0.6312589049339294, 0.3677002191543579, 0.001040796167217195]],
'confidence': [0.6312589049339294]},
{'sentence': 'go with some friends , wait the half hour or so with a cup of joe , and enjoy more than your average breakfast .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['go',
'with',
'some',
'friends',
',',
'wait',
'the',
'half',
'hour',
'or',
'so',
'with',
'a',
'cup',
'of',
'joe',
',',
'and',
'enjoy',
'more',
'than',
'your',
'average',
'breakfast',
'.'],
'aspect': ['cup', 'joe', 'breakfast'],
'position': [[13, 15, 23], [13, 15, 23], [13, 15, 23]],
'sentiment': ['Neutral', 'Neutral', 'Positive'],
'probs': [[0.0003797019016928971, 0.999221920967102, 0.0003983224742114544],
[0.0003096898435615003, 0.998945415019989, 0.000744970457162708],
[0.0008838666835799813, 0.00017132528591901064, 0.9989448189735413]],
'confidence': [0.999221920967102, 0.998945415019989, 0.9989448189735413]},
{'sentence': 'good eats .',
'IOB': ['O', 'B-ASP', 'O'],
'tokens': ['good', 'eats', '.'],
'aspect': ['eats'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00019383960170671344, 0.0002919057442341, 0.9995142221450806]],
'confidence': [0.9995142221450806]},
{'sentence': "i do n ' t know why anyone would want to write a great review about this place .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['i',
'do',
'n',
"'",
't',
'know',
'why',
'anyone',
'would',
'want',
'to',
'write',
'a',
'great',
'review',
'about',
'this',
'place',
'.'],
'aspect': ['place'],
'position': [[17]],
'sentiment': ['Negative'],
'probs': [[0.8960394263267517, 0.0919489786028862, 0.012011579237878323]],
'confidence': [0.8960394263267517]},
{'sentence': 'i have been to this place , folks and it is bad .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['i',
'have',
'been',
'to',
'this',
'place',
',',
'folks',
'and',
'it',
'is',
'bad',
'.'],
'aspect': ['place'],
'position': [[5]],
'sentiment': ['Negative'],
'probs': [[0.9991974234580994, 0.0006244703545235097, 0.000178097965545021]],
'confidence': [0.9991974234580994]},
{'sentence': "maybe it is good for that one night once in a blue moon when the chefs decide to use fish that ' s half - way decent .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['maybe',
'it',
'is',
'good',
'for',
'that',
'one',
'night',
'once',
'in',
'a',
'blue',
'moon',
'when',
'the',
'chefs',
'decide',
'to',
'use',
'fish',
'that',
"'",
's',
'half',
'-',
'way',
'decent',
'.'],
'aspect': ['chefs', 'fish'],
'position': [[15, 19], [15, 19]],
'sentiment': ['Neutral', 'Neutral'],
'probs': [[0.0037619515787810087, 0.9937076568603516, 0.0025303184520453215],
[0.32278743386268616, 0.6730204224586487, 0.004192150663584471]],
'confidence': [0.9937076568603516, 0.6730204224586487]},
{'sentence': 'i have been here , spent tons of money on a chef special dinner and it was a major dissappointment .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'have',
'been',
'here',
',',
'spent',
'tons',
'of',
'money',
'on',
'a',
'chef',
'special',
'dinner',
'and',
'it',
'was',
'a',
'major',
'dissappointment',
'.'],
'aspect': ['money', 'chef special dinner'],
'position': [[8, 11, 12, 13], [8, 11, 12, 13]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9845513701438904, 0.012285010889172554, 0.003163635730743408],
[0.7466579675674438, 0.25297626852989197, 0.00036573680699802935]],
'confidence': [0.9845513701438904, 0.7466579675674438]},
{'sentence': 'fancy pieces of exotic fish on a $ 100 dollar plate and not one was eatable .',
'IOB': ['O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['fancy',
'pieces',
'of',
'exotic',
'fish',
'on',
'a',
'$',
'100',
'dollar',
'plate',
'and',
'not',
'one',
'was',
'eatable',
'.'],
'aspect': ['exotic fish', 'plate'],
'position': [[3, 4, 10], [3, 4, 10]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.013463717885315418, 0.00047898024786263704, 0.9860572814941406],
[0.1550590991973877, 0.8446521759033203, 0.0002887400332838297]],
'confidence': [0.9860572814941406, 0.8446521759033203]},
{'sentence': ' – the atmosphere is great for any special occasion you might want to celebrate .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'the',
'atmosphere',
'is',
'great',
'for',
'any',
'special',
'occasion',
'you',
'might',
'want',
'to',
'celebrate',
'.'],
'aspect': ['the'],
'position': [[2, 15]],
'sentiment': ['Positive'],
'probs': [[0.0001728712086332962,
0.0004209137405268848,
0.9994062185287476]],
'confidence': [0.9994062185287476]},
{'sentence': 'the best dish are the honwy walnut prawns - just outstanding .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'best',
'dish',
'are',
'the',
'honwy',
'walnut',
'prawns',
'-',
'just',
'outstanding',
'.'],
'aspect': ['dish'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.00022637353686150163,
0.00038967092405073345,
0.9993839263916016]],
'confidence': [0.9993839263916016]},
{'sentence': 'the service is really attentive and charming .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'service',
'is',
'really',
'attentive',
'and',
'charming',
'.'],
'aspect': ['service'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00031068798853084445,
0.00022250057372730225,
0.9994668364524841]],
'confidence': [0.9994668364524841]},
{'sentence': 'the service was excellent , the coffee was good even by starbucks standards and the food was outstanding .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['the',
'service',
'was',
'excellent',
',',
'the',
'coffee',
'was',
'good',
'even',
'by',
'starbucks',
'standards',
'and',
'the',
'food',
'was',
'outstanding',
'.'],
'aspect': ['service', 'coffee', 'food'],
'position': [[1, 6, 15], [1, 6, 15], [1, 6, 15]],
'sentiment': ['Positive', 'Positive', 'Positive'],
'probs': [[0.00041182772838510573,
0.00026762360357679427,
0.9993205070495605],
[0.00018059050489682704, 0.00038821768248453736, 0.9994311928749084],
[0.00014137724065221846, 0.00046709360321983695, 0.9993914365768433]],
'confidence': [0.9993205070495605, 0.9994311928749084, 0.9993914365768433]},
{'sentence': ' – i recently had the pleasure of dining as this delightful restaurant on 2nd street and wow what a great evening we had .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'recently',
'had',
'the',
'pleasure',
'of',
'dining',
'as',
'this',
'delightful',
'restaurant',
'on',
'2nd',
'street',
'and',
'wow',
'what',
'a',
'great',
'evening',
'we',
'had',
'.'],
'aspect': ['of'],
'position': [[7, 24]],
'sentiment': ['Positive'],
'probs': [[0.00017989674233831465,
0.00029163609724491835,
0.9995284080505371]],
'confidence': [0.9995284080505371]},
{'sentence': 'the food is fantastic , authentic , delicious and very , very affordable .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'food',
'is',
'fantastic',
',',
'authentic',
',',
'delicious',
'and',
'very',
',',
'very',
'affordable',
'.'],
'aspect': ['food'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00024643298820592463,
0.00023251731181517243,
0.9995211362838745]],
'confidence': [0.9995211362838745]},
{'sentence': 'the decor was beautiful and unique .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the', 'decor', 'was', 'beautiful', 'and', 'unique', '.'],
'aspect': ['decor'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00019940486527048051,
0.0002612951211631298,
0.9995392560958862]],
'confidence': [0.9995392560958862]},
{'sentence': 'there was a really nice vibe about the place . . . good music , atmosphere and happy looking people .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['there',
'was',
'a',
'really',
'nice',
'vibe',
'about',
'the',
'place',
'.',
'.',
'.',
'good',
'music',
',',
'atmosphere',
'and',
'happy',
'looking',
'people',
'.'],
'aspect': ['vibe', 'place', 'music', 'atmosphere', 'people'],
'position': [[5, 8, 13, 15, 19],
[5, 8, 13, 15, 19],
[5, 8, 13, 15, 19],
[5, 8, 13, 15, 19],
[5, 8, 13, 15, 19]],
'sentiment': ['Positive', 'Positive', 'Positive', 'Positive', 'Positive'],
'probs': [[0.00015524249465670437, 0.003244493855163455, 0.9966002106666565],
[0.0001865788799477741, 0.039812419563531876, 0.9600010514259338],
[0.00014256295980885625, 0.0005013935151509941, 0.9993559718132019],
[0.0001865747181000188, 0.00029700869345106184, 0.9995163679122925],
[0.00021975339041091502, 0.0002564054448157549, 0.9995238780975342]],
'confidence': [0.9966002106666565,
0.9600010514259338,
0.9993559718132019,
0.9995163679122925,
0.9995238780975342]},
{'sentence': 'our server was very professional and friendly .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['our',
'server',
'was',
'very',
'professional',
'and',
'friendly',
'.'],
'aspect': ['server'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00018857490795198828,
0.0002868899318855256,
0.9995244741439819]],
'confidence': [0.9995244741439819]},
{'sentence': "to the owners of open sesame . . . bravo . . . i ca n ' t wait to come back to dine at your restaurant !",
'IOB': ['O',
'O',
'B-ASP',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['to',
'the',
'owners',
'of',
'open',
'sesame',
'.',
'.',
'.',
'bravo',
'.',
'.',
'.',
'i',
'ca',
'n',
"'",
't',
'wait',
'to',
'come',
'back',
'to',
'dine',
'at',
'your',
'restaurant',
'!'],
'aspect': ['owners', 'open sesame'],
'position': [[2, 4, 5], [2, 4, 5]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0007593686459586024, 0.0010060033528134227, 0.9982346296310425],
[0.0003363958967383951, 0.6071572303771973, 0.3925063908100128]],
'confidence': [0.9982346296310425, 0.6071572303771973]},
{'sentence': "it ' s a tiny place so if you get there before 8 pm on a weekend ( thurs ? sun ) you will find it easier to get a table or a seat at the sushi bar .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O'],
'tokens': ['it',
"'",
's',
'a',
'tiny',
'place',
'so',
'if',
'you',
'get',
'there',
'before',
'8',
'pm',
'on',
'a',
'weekend',
'(',
'thurs',
'?',
'sun',
')',
'you',
'will',
'find',
'it',
'easier',
'to',
'get',
'a',
'table',
'or',
'a',
'seat',
'at',
'the',
'sushi',
'bar',
'.'],
'aspect': ['place', 'sushi bar'],
'position': [[5, 36, 37], [5, 36, 37]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9293291568756104, 0.06824596971273422, 0.0024248454719781876],
[0.0009632460423745215, 0.9984897375106812, 0.0005470463074743748]],
'confidence': [0.9293291568756104, 0.9984897375106812]},
{'sentence': 'everything , and i mean everything on the menu is delectable .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['everything',
',',
'and',
'i',
'mean',
'everything',
'on',
'the',
'menu',
'is',
'delectable',
'.'],
'aspect': ['menu'],
'position': [[8]],
'sentiment': ['Positive'],
'probs': [[0.00014359834312926978,
0.0009884040337055922,
0.9988679885864258]],
'confidence': [0.9988679885864258]},
{'sentence': 'the waiters are very experienced and helpful with pairing your drink choice to your food tastes or vice versa .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'waiters',
'are',
'very',
'experienced',
'and',
'helpful',
'with',
'pairing',
'your',
'drink',
'choice',
'to',
'your',
'food',
'tastes',
'or',
'vice',
'versa',
'.'],
'aspect': ['waiters', 'drink', 'food'],
'position': [[1, 10, 14], [1, 10, 14], [1, 10, 14]],
'sentiment': ['Positive', 'Neutral', 'Neutral'],
'probs': [[0.001084002899006009, 0.00017375816241838038, 0.9987422823905945],
[0.00023483792028855532, 0.9991288781166077, 0.0006362439598888159],
[0.000270163087407127, 0.9992709755897522, 0.00045884118298999965]],
'confidence': [0.9987422823905945, 0.9991288781166077, 0.9992709755897522]},
{'sentence': "the sushi is as fresh as it comes ? you ' d think ocean was in their backyard , no joke !",
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'sushi',
'is',
'as',
'fresh',
'as',
'it',
'comes',
'?',
'you',
"'",
'd',
'think',
'ocean',
'was',
'in',
'their',
'backyard',
',',
'no',
'joke',
'!'],
'aspect': ['sushi'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.00044490251457318664,
0.00020310122636146843,
0.9993519186973572]],
'confidence': [0.9993519186973572]},
{'sentence': "if you ' re interested in good tasting ( without the fish taste or smell ) , large portions and creative sushi dishes this is your place . . .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['if',
'you',
"'",
're',
'interested',
'in',
'good',
'tasting',
'(',
'without',
'the',
'fish',
'taste',
'or',
'smell',
')',
',',
'large',
'portions',
'and',
'creative',
'sushi',
'dishes',
'this',
'is',
'your',
'place',
'.',
'.',
'.'],
'aspect': ['fish', 'portions', 'sushi dishes'],
'position': [[11, 18, 21, 22], [11, 18, 21, 22], [11, 18, 21, 22]],
'sentiment': ['Neutral', 'Positive', 'Positive'],
'probs': [[0.001973366364836693, 0.997494101524353, 0.000532530015334487],
[0.0004921359941363335, 0.012811538763344288, 0.9866963028907776],
[0.00026187600451521575, 0.00020415434846654534, 0.999534010887146]],
'confidence': [0.997494101524353, 0.9866963028907776, 0.999534010887146]},
{'sentence': 'big thick pepperoni',
'IOB': ['O', 'O', 'B-ASP'],
'tokens': ['big', 'thick', 'pepperoni'],
'aspect': ['pepperoni'],
'position': [[2]],
'sentiment': ['Positive'],
'probs': [[0.006196534261107445, 0.002213341649621725, 0.9915902018547058]],
'confidence': [0.9915902018547058]},
{'sentence': " – the pepperoni ' s cut real thick - - yum .",
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'the',
'pepperoni',
"'",
's',
'cut',
'real',
'thick',
'-',
'-',
'yum',
'.'],
'aspect': ['the'],
'position': [[2, 12]],
'sentiment': ['Positive'],
'probs': [[0.28997349739074707, 0.07237911969423294, 0.6376473307609558]],
'confidence': [0.6376473307609558]},
{'sentence': "the pizza itself is not exactly the best i ' ve had ever , but still pretty good .",
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'pizza',
'itself',
'is',
'not',
'exactly',
'the',
'best',
'i',
"'",
've',
'had',
'ever',
',',
'but',
'still',
'pretty',
'good',
'.'],
'aspect': ['pizza'],
'position': [[1]],
'sentiment': ['Neutral'],
'probs': [[0.009491907432675362, 0.7601072192192078, 0.23040086030960083]],
'confidence': [0.7601072192192078]},
{'sentence': 'sit in the balcony',
'IOB': ['O', 'O', 'O', 'B-ASP'],
'tokens': ['sit', 'in', 'the', 'balcony'],
'aspect': ['balcony'],
'position': [[3]],
'sentiment': ['Neutral'],
'probs': [[0.0007081333897076547, 0.9986287355422974, 0.000663203012663871]],
'confidence': [0.9986287355422974]},
{'sentence': 'food was good and appetizing .',
'IOB': ['B-ASP', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['food', 'was', 'good', 'and', 'appetizing', '.'],
'aspect': ['food'],
'position': [[0]],
'sentiment': ['Positive'],
'probs': [[0.00014304081560112536,
0.0007013655267655849,
0.9991556406021118]],
'confidence': [0.9991556406021118]},
{'sentence': 'portions was just enough for me , but may not be for a big eater .',
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['portions',
'was',
'just',
'enough',
'for',
'me',
',',
'but',
'may',
'not',
'be',
'for',
'a',
'big',
'eater',
'.'],
'aspect': ['portions'],
'position': [[0]],
'sentiment': ['Positive'],
'probs': [[0.001108443015255034, 0.0005403384566307068, 0.9983512163162231]],
'confidence': [0.9983512163162231]},
{'sentence': 'fair menu selection .',
'IOB': ['O', 'B-ASP', 'O', 'O'],
'tokens': ['fair', 'menu', 'selection', '.'],
'aspect': ['menu'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0009552746778354049, 0.10045072436332703, 0.8985939621925354]],
'confidence': [0.8985939621925354]},
{'sentence': 'the appetizer was interesting , but the creme brulee was very savory and delicious .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'appetizer',
'was',
'interesting',
',',
'but',
'the',
'creme',
'brulee',
'was',
'very',
'savory',
'and',
'delicious',
'.'],
'aspect': ['appetizer', 'creme brulee'],
'position': [[1, 7, 8], [1, 7, 8]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0002470270555932075,
0.00044652618817053735,
0.9993064403533936],
[0.004139593802392483, 0.0002418791118543595, 0.9956185221672058]],
'confidence': [0.9993064403533936, 0.9956185221672058]},
{'sentence': 'indoor ambience was modern .',
'IOB': ['B-ASP', 'I-ASP', 'O', 'O', 'O'],
'tokens': ['indoor', 'ambience', 'was', 'modern', '.'],
'aspect': ['indoor ambience'],
'position': [[0, 1]],
'sentiment': ['Positive'],
'probs': [[0.0001389398967148736,
0.0012499464210122824,
0.9986110925674438]],
'confidence': [0.9986110925674438]},
{'sentence': "if it ' s nice outside , request for a table in the balcony .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['if',
'it',
"'",
's',
'nice',
'outside',
',',
'request',
'for',
'a',
'table',
'in',
'the',
'balcony',
'.'],
'aspect': ['table', 'balcony'],
'position': [[10, 13], [10, 13]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0007927154074423015, 0.15287458896636963, 0.8463327288627625],
[0.00044773967238143086, 0.7201805114746094, 0.2793716788291931]],
'confidence': [0.8463327288627625, 0.7201805114746094]},
{'sentence': "it ' s a great place to people watch .",
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O', 'O', 'O', 'O'],
'tokens': ['it',
"'",
's',
'a',
'great',
'place',
'to',
'people',
'watch',
'.'],
'aspect': ['place'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.0005091141792945564,
0.00026084986166097224,
0.9992300271987915]],
'confidence': [0.9992300271987915]},
{'sentence': 'although the service could be improved considering the money you put in .',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['although',
'the',
'service',
'could',
'be',
'improved',
'considering',
'the',
'money',
'you',
'put',
'in',
'.'],
'aspect': ['service'],
'position': [[2]],
'sentiment': ['Negative'],
'probs': [[0.9961138963699341, 0.003234298201277852, 0.0006517692236229777]],
'confidence': [0.9961138963699341]},
{'sentence': 'our drinks kept coming but our server came by a couple times .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['our',
'drinks',
'kept',
'coming',
'but',
'our',
'server',
'came',
'by',
'a',
'couple',
'times',
'.'],
'aspect': ['drinks', 'server'],
'position': [[1, 6], [1, 6]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.0002674745919648558, 0.7026894688606262, 0.2970430552959442],
[0.9990633130073547, 0.0006912267999723554, 0.0002454796340316534]],
'confidence': [0.7026894688606262, 0.9990633130073547]},
{'sentence': 'late night dinning with exeptional food .',
'IOB': ['O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['late', 'night', 'dinning', 'with', 'exeptional', 'food', '.'],
'aspect': ['food'],
'position': [[5]],
'sentiment': ['Positive'],
'probs': [[0.0004455667803995311,
0.00017724749341141433,
0.9993771910667419]],
'confidence': [0.9993771910667419]},
{'sentence': 'we were seated right away , the table was private and nice .',
'IOB': ['O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['we',
'were',
'seated',
'right',
'away',
',',
'the',
'table',
'was',
'private',
'and',
'nice',
'.'],
'aspect': ['seated', 'table'],
'position': [[2, 7], [2, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00017274709534831345, 0.000455415400210768, 0.9993718266487122],
[0.0001447549875592813, 0.0004125628911424428, 0.9994426369667053]],
'confidence': [0.9993718266487122, 0.9994426369667053]},
{'sentence': 'the service was exceptional - sometime there was a feeling that we were served by the army of friendly waiters .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'service',
'was',
'exceptional',
'-',
'sometime',
'there',
'was',
'a',
'feeling',
'that',
'we',
'were',
'served',
'by',
'the',
'army',
'of',
'friendly',
'waiters',
'.'],
'aspect': ['service', 'waiters'],
'position': [[1, 19], [1, 19]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0035411790013313293, 0.0005706093506887555, 0.9958882927894592],
[0.00032971217297017574, 0.004285117145627737, 0.9953851103782654]],
'confidence': [0.9958882927894592, 0.9953851103782654]},
{'sentence': "the food was very good , filet mignon was probably the best i ' ve ever try .",
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'food',
'was',
'very',
'good',
',',
'filet',
'mignon',
'was',
'probably',
'the',
'best',
'i',
"'",
've',
'ever',
'try',
'.'],
'aspect': ['food', 'filet mignon'],
'position': [[1, 6, 7], [1, 6, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00021883059525862336,
0.00036452518543228507,
0.9994165897369385],
[0.00021892182121519, 0.0002853708283510059, 0.9994957447052002]],
'confidence': [0.9994165897369385, 0.9994957447052002]},
{'sentence': 'the portions are big though , so do not order too much .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
'tokens': ['the',
'portions',
'are',
'big',
'though',
',',
'so',
'do',
'not',
'order',
'too',
'much',
'.'],
'aspect': ['portions'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0005873613408766687,
0.0003019070136360824,
0.9991106390953064]],
'confidence': [0.9991106390953064]},
{'sentence': 'groovy music made the dinner casual .',
'IOB': ['O', 'B-ASP', 'O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['groovy', 'music', 'made', 'the', 'dinner', 'casual', '.'],
'aspect': ['music', 'dinner'],
'position': [[1, 4], [1, 4]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.01639099419116974, 0.0004049065464641899, 0.9832041263580322],
[0.000845838978420943, 0.9984813332557678, 0.0006728628068231046]],
'confidence': [0.9832041263580322, 0.9984813332557678]},
{'sentence': 'i have a but here - there was a bathroom attendant in the restroom which was odd .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'have',
'a',
'but',
'here',
'-',
'there',
'was',
'a',
'bathroom',
'attendant',
'in',
'the',
'restroom',
'which',
'was',
'odd',
'.'],
'aspect': ['bathroom attendant'],
'position': [[9, 10]],
'sentiment': ['Negative'],
'probs': [[0.9731176495552063, 0.024813925847411156, 0.0020683964248746634]],
'confidence': [0.9731176495552063]},
{'sentence': 'the bathroom itself is very small with two toilets and only one sink , the girl was staying totally on the way hanging out paper towels from the dispenser .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'bathroom',
'itself',
'is',
'very',
'small',
'with',
'two',
'toilets',
'and',
'only',
'one',
'sink',
',',
'the',
'girl',
'was',
'staying',
'totally',
'on',
'the',
'way',
'hanging',
'out',
'paper',
'towels',
'from',
'the',
'dispenser',
'.'],
'aspect': ['bathroom', 'toilets', 'sink', 'towels', 'dispenser'],
'position': [[1, 8, 12, 25, 28],
[1, 8, 12, 25, 28],
[1, 8, 12, 25, 28],
[1, 8, 12, 25, 28],
[1, 8, 12, 25, 28]],
'sentiment': ['Negative', 'Neutral', 'Negative', 'Negative', 'Negative'],
'probs': [[0.8785225749015808, 0.1207367330789566, 0.0007406054646708071],
[0.25284668803215027, 0.7465387582778931, 0.0006145520019344985],
[0.9687321186065674, 0.02888473868370056, 0.002383037470281124],
[0.7734652161598206, 0.2260809987783432, 0.00045377638889476657],
[0.5790677070617676, 0.42047497630119324, 0.00045731483260169625]],
'confidence': [0.8785225749015808,
0.7465387582778931,
0.9687321186065674,
0.7734652161598206,
0.5790677070617676]},
{'sentence': 'this place rocks ! !',
'IOB': ['O', 'B-ASP', 'O', 'O', 'O'],
'tokens': ['this', 'place', 'rocks', '!', '!'],
'aspect': ['place'],
'position': [[1]],
'sentiment': ['Positive'],
'probs': [[0.0002630274393595755,
0.00023603971931152046,
0.9995008707046509]],
'confidence': [0.9995008707046509]},
{'sentence': ' – mercedes restaurant is so tasty , the service is undeniably awesome !',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'mercedes',
'restaurant',
'is',
'so',
'tasty',
',',
'the',
'service',
'is',
'undeniably',
'awesome',
'!'],
'aspect': ['the'],
'position': [[8, 13]],
'sentiment': ['Positive'],
'probs': [[0.00021439777628984302,
0.0003147232346236706,
0.9994710087776184]],
'confidence': [0.9994710087776184]},
{'sentence': 'the chips and salsa are so yummy , and the prices are fabulous .',
'IOB': ['O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O'],
'tokens': ['the',
'chips',
'and',
'salsa',
'are',
'so',
'yummy',
',',
'and',
'the',
'prices',
'are',
'fabulous',
'.'],
'aspect': ['chips and salsa', 'prices'],
'position': [[1, 2, 3, 10], [1, 2, 3, 10]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00017494398343842477,
0.00028260968974791467,
0.9995424747467041],
[0.0002898538368754089, 0.0002624376502353698, 0.9994476437568665]],
'confidence': [0.9995424747467041, 0.9994476437568665]},
{'sentence': 'the atmosphere is aspiring , and the decor is festive and amazing . .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'atmosphere',
'is',
'aspiring',
',',
'and',
'the',
'decor',
'is',
'festive',
'and',
'amazing',
'.',
'.'],
'aspect': ['atmosphere', 'decor'],
'position': [[1, 7], [1, 7]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00013188825687393546,
0.0020714937709271908,
0.9977966547012329],
[0.00015947336214594543, 0.0004214855143800378, 0.9994189739227295]],
'confidence': [0.9977966547012329, 0.9994189739227295]},
{'sentence': 'the catering is out of this world , and raouls chicken vegetable soup rocks my world ! ! !',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'catering',
'is',
'out',
'of',
'this',
'world',
',',
'and',
'raouls',
'chicken',
'vegetable',
'soup',
'rocks',
'my',
'world',
'!',
'!',
'!'],
'aspect': ['catering', 'chicken vegetable soup'],
'position': [[1, 10, 11, 12], [1, 10, 11, 12]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00020982119895052165,
0.00028248937451280653,
0.9995076656341553],
[0.0002713995927479118, 0.00032582710264250636, 0.9994027614593506]],
'confidence': [0.9995076656341553, 0.9994027614593506]},
{'sentence': 'drinks are suberb , and i feel like i am in a third world country when i walk in the door .',
'IOB': ['B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['drinks',
'are',
'suberb',
',',
'and',
'i',
'feel',
'like',
'i',
'am',
'in',
'a',
'third',
'world',
'country',
'when',
'i',
'walk',
'in',
'the',
'door',
'.'],
'aspect': ['drinks'],
'position': [[0]],
'sentiment': ['Negative'],
'probs': [[0.5774502158164978, 0.42197713255882263, 0.000572563149034977]],
'confidence': [0.5774502158164978]},
{'sentence': '- mediocre service / quality',
'IOB': ['O', 'O', 'B-ASP', 'O', 'O'],
'tokens': ['-', 'mediocre', 'service', '/', 'quality'],
'aspect': ['service'],
'position': [[2]],
'sentiment': ['Neutral'],
'probs': [[0.006231270730495453, 0.9929303526878357, 0.0008384360116906464]],
'confidence': [0.9929303526878357]},
{'sentence': 'the presentation of snooze is excellent and it is one of those places that you feel more sophisticated just for being there ; but peel back the layers and you have an overpriced ihop with a high brow menu .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['the',
'presentation',
'of',
'snooze',
'is',
'excellent',
'and',
'it',
'is',
'one',
'of',
'those',
'places',
'that',
'you',
'feel',
'more',
'sophisticated',
'just',
'for',
'being',
'there',
';',
'but',
'peel',
'back',
'the',
'layers',
'and',
'you',
'have',
'an',
'overpriced',
'ihop',
'with',
'a',
'high',
'brow',
'menu',
'.'],
'aspect': ['ihop', 'menu'],
'position': [[33, 38], [33, 38]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.9951761960983276, 0.004398170858621597, 0.0004256124375388026],
[0.7155869007110596, 0.006291086785495281, 0.2781219780445099]],
'confidence': [0.9951761960983276, 0.7155869007110596]},
{'sentence': 'to start off , approximately 8 - 10 oz of orange juice will cost you $ 3 .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O'],
'tokens': ['to',
'start',
'off',
',',
'approximately',
'8',
'-',
'10',
'oz',
'of',
'orange',
'juice',
'will',
'cost',
'you',
'$',
'3',
'.'],
'aspect': ['orange juice', 'cost'],
'position': [[10, 11, 13], [10, 11, 13]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.06724364310503006, 0.9318297505378723, 0.0009266273118555546],
[0.7048162817955017, 0.2888669967651367, 0.006316679064184427]],
'confidence': [0.9318297505378723, 0.7048162817955017]},
{'sentence': 'they serve it in a tall , skinny hour - glass shaped glass to disguise the fact that you a getting a small juice at the price of a half gallon in a supermarket .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['they',
'serve',
'it',
'in',
'a',
'tall',
',',
'skinny',
'hour',
'-',
'glass',
'shaped',
'glass',
'to',
'disguise',
'the',
'fact',
'that',
'you',
'a',
'getting',
'a',
'small',
'juice',
'at',
'the',
'price',
'of',
'a',
'half',
'gallon',
'in',
'a',
'supermarket',
'.'],
'aspect': ['serve', 'glass', 'price'],
'position': [[1, 12, 26], [1, 12, 26], [1, 12, 26]],
'sentiment': ['Negative', 'Negative', 'Neutral'],
'probs': [[0.8474224805831909, 0.1509457528591156, 0.001631830120459199],
[0.8286852836608887, 0.05875585600733757, 0.11255891621112823],
[0.043991874903440475, 0.9556460976600647, 0.0003619928320404142]],
'confidence': [0.8474224805831909, 0.8286852836608887, 0.9556460976600647]},
{'sentence': 'i should have just asked for the check when i saw that ; but their menu was so unique that i continued .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'should',
'have',
'just',
'asked',
'for',
'the',
'check',
'when',
'i',
'saw',
'that',
';',
'but',
'their',
'menu',
'was',
'so',
'unique',
'that',
'i',
'continued',
'.'],
'aspect': ['check', 'menu'],
'position': [[7, 15], [7, 15]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.0004523300158325583,
0.9991372227668762,
0.00041046112892217934],
[0.0006235272157937288, 0.00020752183627337217, 0.9991689920425415]],
'confidence': [0.9991372227668762, 0.9991689920425415]},
{'sentence': 'the pancakes were certainly inventive but $ 8 . 50 for 3 - 6 " pancakes ( one of them was more like 5 " ) in the pancake flight ( sample of 3 different pancakes ) is well over - priced .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'pancakes',
'were',
'certainly',
'inventive',
'but',
'$',
'8',
'.',
'50',
'for',
'3',
'-',
'6',
'"',
'pancakes',
'(',
'one',
'of',
'them',
'was',
'more',
'like',
'5',
'"',
')',
'in',
'the',
'pancake',
'flight',
'(',
'sample',
'of',
'3',
'different',
'pancakes',
')',
'is',
'well',
'over',
'-',
'priced',
'.'],
'aspect': ['pancakes', 'pancake'],
'position': [[1, 28], [1, 28]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.34878647327423096, 0.01023164764046669, 0.6409818530082703],
[0.3524862229824066, 0.01022486574947834, 0.6372888684272766]],
'confidence': [0.6409818530082703, 0.6372888684272766]},
{'sentence': 'the pancakes should be larger ( at least 8 " ) to justify the expense even with the unique offerings .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'pancakes',
'should',
'be',
'larger',
'(',
'at',
'least',
'8',
'"',
')',
'to',
'justify',
'the',
'expense',
'even',
'with',
'the',
'unique',
'offerings',
'.'],
'aspect': ['pancakes', 'expense'],
'position': [[1, 14], [1, 14]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.845134973526001, 0.0003966004296671599, 0.1544683575630188],
[0.02832946367561817, 0.9695382714271545, 0.002132310764864087]],
'confidence': [0.845134973526001, 0.9695382714271545]},
{'sentence': "on my meal i had to send back my eggs for a simple request of breaking the yokes before cooking , and would have had to send them back again if i had n ' t rejected the meal all together .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['on',
'my',
'meal',
'i',
'had',
'to',
'send',
'back',
'my',
'eggs',
'for',
'a',
'simple',
'request',
'of',
'breaking',
'the',
'yokes',
'before',
'cooking',
',',
'and',
'would',
'have',
'had',
'to',
'send',
'them',
'back',
'again',
'if',
'i',
'had',
'n',
"'",
't',
'rejected',
'the',
'meal',
'all',
'together',
'.'],
'aspect': ['eggs', 'yokes'],
'position': [[9, 17], [9, 17]],
'sentiment': ['Negative', 'Negative'],
'probs': [[0.995261549949646, 0.0043937815353274345, 0.00034470533137209713],
[0.9980871677398682, 0.0016958629712462425, 0.0002170515072066337]],
'confidence': [0.995261549949646, 0.9980871677398682]},
{'sentence': 'i rejected it because in the process of attempting to fix the eggs they broke something else in the dish and i was too frustrated to continue .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'rejected',
'it',
'because',
'in',
'the',
'process',
'of',
'attempting',
'to',
'fix',
'the',
'eggs',
'they',
'broke',
'something',
'else',
'in',
'the',
'dish',
'and',
'i',
'was',
'too',
'frustrated',
'to',
'continue',
'.'],
'aspect': ['eggs', 'dish'],
'position': [[12, 19], [12, 19]],
'sentiment': ['Negative', 'Neutral'],
'probs': [[0.9992089867591858, 0.0005205913330428302, 0.0002705198712646961],
[0.0005609449581243098, 0.9989545345306396, 0.00048454481293447316]],
'confidence': [0.9992089867591858, 0.9989545345306396]},
{'sentence': 'to their credit they removed the dish from the check ; but no manager stopped by to ask what the problem was .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['to',
'their',
'credit',
'they',
'removed',
'the',
'dish',
'from',
'the',
'check',
';',
'but',
'no',
'manager',
'stopped',
'by',
'to',
'ask',
'what',
'the',
'problem',
'was',
'.'],
'aspect': ['dish', 'manager'],
'position': [[6, 13], [6, 13]],
'sentiment': ['Neutral', 'Negative'],
'probs': [[0.00024039809068199247,
0.9986862540245056,
0.0010733145754784346],
[0.9991334080696106, 0.0004782352480106056, 0.0003884633770212531]],
'confidence': [0.9986862540245056, 0.9991334080696106]},
{'sentence': 'in the end our check came to $ 27 for 4 small pancakes , a breakfast burrito , an orange juice and an iced tea ( i had water ) .',
'IOB': ['O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'O'],
'tokens': ['in',
'the',
'end',
'our',
'check',
'came',
'to',
'$',
'27',
'for',
'4',
'small',
'pancakes',
',',
'a',
'breakfast',
'burrito',
',',
'an',
'orange',
'juice',
'and',
'an',
'iced',
'tea',
'(',
'i',
'had',
'water',
')',
'.'],
'aspect': ['check',
'pancakes',
'breakfast burrito',
'orange juice',
'iced tea',
'water'],
'position': [[4, 12, 15, 16, 19, 20, 23, 24, 28],
[4, 12, 15, 16, 19, 20, 23, 24, 28],
[4, 12, 15, 16, 19, 20, 23, 24, 28],
[4, 12, 15, 16, 19, 20, 23, 24, 28],
[4, 12, 15, 16, 19, 20, 23, 24, 28],
[4, 12, 15, 16, 19, 20, 23, 24, 28]],
'sentiment': ['Neutral',
'Negative',
'Neutral',
'Neutral',
'Neutral',
'Neutral'],
'probs': [[0.002156417816877365, 0.9972398281097412, 0.0006037381826899946],
[0.9039381742477417, 0.09510353952646255, 0.0009582535712979734],
[0.05665704980492592, 0.9429887533187866, 0.0003542510967236012],
[0.01467626541852951, 0.9849721789360046, 0.00035159484832547605],
[0.009661826305091381, 0.9899216294288635, 0.0004165186546742916],
[0.0015454440144822001, 0.9978523254394531, 0.0006023086607456207]],
'confidence': [0.9972398281097412,
0.9039381742477417,
0.9429887533187866,
0.9849721789360046,
0.9899216294288635,
0.9978523254394531]},
{'sentence': 'much more than just a great view !',
'IOB': ['O', 'O', 'O', 'O', 'O', 'O', 'B-ASP', 'O'],
'tokens': ['much', 'more', 'than', 'just', 'a', 'great', 'view', '!'],
'aspect': ['view'],
'position': [[6]],
'sentiment': ['Positive'],
'probs': [[0.000204637210117653,
0.00025362250744365156,
0.9995417594909668]],
'confidence': [0.9995417594909668]},
{'sentence': " – i am exceedingly pleased to report that my dinner at ray ' s boathouse last friday completely exceeded my expectations .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'[SEP]'],
'tokens': [' ',
'–',
'i',
'am',
'exceedingly',
'pleased',
'to',
'report',
'that',
'my',
'dinner',
'at',
'ray',
"'",
's',
'boathouse',
'last',
'friday',
'completely',
'exceeded',
'my',
'expectations',
'.'],
'aspect': ['my', 'at'],
'position': [[9, 11, 22], [9, 11, 22]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.00021399006072897464,
0.0002730815904214978,
0.9995129108428955],
[0.0002146019833162427, 0.00027416800730861723, 0.9995112419128418]],
'confidence': [0.9995129108428955, 0.9995112419128418]},
{'sentence': "ray ' s is something of a seattle institution , but given its gorgeous sound views , i had suspected that the accolades were more due to the scenery than to the food and service .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O'],
'tokens': ['ray',
"'",
's',
'is',
'something',
'of',
'a',
'seattle',
'institution',
',',
'but',
'given',
'its',
'gorgeous',
'sound',
'views',
',',
'i',
'had',
'suspected',
'that',
'the',
'accolades',
'were',
'more',
'due',
'to',
'the',
'scenery',
'than',
'to',
'the',
'food',
'and',
'service',
'.'],
'aspect': ['sound views', 'scenery', 'food', 'service'],
'position': [[14, 15, 28, 32, 34],
[14, 15, 28, 32, 34],
[14, 15, 28, 32, 34],
[14, 15, 28, 32, 34]],
'sentiment': ['Positive', 'Neutral', 'Neutral', 'Neutral'],
'probs': [[0.0007435608422383666,
0.00023522884293925017,
0.9990211725234985],
[0.001192539231851697, 0.9645717740058899, 0.034235674887895584],
[0.03346181660890579, 0.9659597277641296, 0.0005784228560514748],
[0.05666166543960571, 0.9429661631584167, 0.0003721860412042588]],
'confidence': [0.9990211725234985,
0.9645717740058899,
0.9659597277641296,
0.9429661631584167]},
{'sentence': "imagine my happy surprise upon finding that the views are only the third - best thing about ray ' s !",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['imagine',
'my',
'happy',
'surprise',
'upon',
'finding',
'that',
'the',
'views',
'are',
'only',
'the',
'third',
'-',
'best',
'thing',
'about',
'ray',
"'",
's',
'!'],
'aspect': ['views'],
'position': [[8]],
'sentiment': ['Positive'],
'probs': [[0.0002976885880343616, 0.000560862710699439, 0.9991414546966553]],
'confidence': [0.9991414546966553]},
{'sentence': 'to start things off , our lovely server brooke was quickly on hand to take my drink order .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O'],
'tokens': ['to',
'start',
'things',
'off',
',',
'our',
'lovely',
'server',
'brooke',
'was',
'quickly',
'on',
'hand',
'to',
'take',
'my',
'drink',
'order',
'.'],
'aspect': ['server', 'drink'],
'position': [[7, 16], [7, 16]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0005055267829447985,
0.00018558047304395586,
0.9993088245391846],
[0.0002658283046912402, 0.9992873072624207, 0.0004468379484023899]],
'confidence': [0.9993088245391846, 0.9992873072624207]},
{'sentence': "my party of two was feeling particularly ambitious , and we splurged on the shilshole sampler . . . a beautiful assortment of enormous white gulf prawns , smoked albacore tuna , ray ' s fantastic manila clams seasoned with dill , scallops in a tasty soy dressing , and a tiny pile of dungeness crab atop a sublime butter sauce .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'I-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O'],
'tokens': ['my',
'party',
'of',
'two',
'was',
'feeling',
'particularly',
'ambitious',
',',
'and',
'we',
'splurged',
'on',
'the',
'shilshole',
'sampler',
'.',
'.',
'.',
'a',
'beautiful',
'assortment',
'of',
'enormous',
'white',
'gulf',
'prawns',
',',
'smoked',
'albacore',
'tuna',
',',
'ray',
"'",
's',
'fantastic',
'manila',
'clams',
'seasoned',
'with',
'dill',
',',
'scallops',
'in',
'a',
'tasty',
'soy',
'dressing',
',',
'and',
'a',
'tiny',
'pile',
'of',
'dungeness',
'crab',
'atop',
'a',
'sublime',
'butter',
'sauce',
'.'],
'aspect': ['assortment',
'white gulf prawns',
'smoked albacore tuna',
'manila clams seasoned with dill',
'scallops',
'soy dressing',
'dungeness crab',
'butter sauce'],
'position': [[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60],
[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60],
[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60],
[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60],
[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60],
[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60],
[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60],
[21,
24,
25,
26,
28,
29,
30,
36,
37,
38,
39,
40,
42,
46,
47,
54,
55,
59,
60]],
'sentiment': ['Positive',
'Positive',
'Positive',
'Neutral',
'Neutral',
'Neutral',
'Neutral',
'Positive'],
'probs': [[0.0007086456753313541, 0.03125159814953804, 0.9680396914482117],
[0.0006575476727448404, 0.44109010696411133, 0.5582523345947266],
[0.0005944010918028653, 0.4987567365169525, 0.5006489157676697],
[0.0005527359899133444, 0.7021358609199524, 0.297311395406723],
[0.0008529346087016165, 0.7425550222396851, 0.2565920352935791],
[0.0006243375246413052, 0.9104409217834473, 0.08893471211194992],
[0.00032787586678750813, 0.9757413268089294, 0.023930788040161133],
[0.00039952987572178245, 0.03814271092414856, 0.9614577293395996]],
'confidence': [0.9680396914482117,
0.5582523345947266,
0.5006489157676697,
0.7021358609199524,
0.7425550222396851,
0.9104409217834473,
0.9757413268089294,
0.9614577293395996]},
{'sentence': 'for my entr & eacute ; e , i completely enjoyed the seared alaskan sea scallops complemented by chard , artichoke hearts , fennel , and pecorino toscano .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['for',
'my',
'entr',
'&',
'eacute',
';',
'e',
',',
'i',
'completely',
'enjoyed',
'the',
'seared',
'alaskan',
'sea',
'scallops',
'complemented',
'by',
'chard',
',',
'artichoke',
'hearts',
',',
'fennel',
',',
'and',
'pecorino',
'toscano',
'.'],
'aspect': ['sea scallops', 'artichoke hearts', 'fennel'],
'position': [[14, 15, 20, 21, 23],
[14, 15, 20, 21, 23],
[14, 15, 20, 21, 23]],
'sentiment': ['Neutral', 'Neutral', 'Neutral'],
'probs': [[0.0011073866626247764, 0.5509985685348511, 0.44789403676986694],
[0.0002869524178095162, 0.9991293549537659, 0.000583737506531179],
[0.0003172449942212552, 0.999106228351593, 0.0005764562520198524]],
'confidence': [0.5509985685348511, 0.9991293549537659, 0.999106228351593]},
{'sentence': 'the scallops are apparently cooked in a black olive butter which really makes them unique ( not to mention tasty ) .',
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['the',
'scallops',
'are',
'apparently',
'cooked',
'in',
'a',
'black',
'olive',
'butter',
'which',
'really',
'makes',
'them',
'unique',
'(',
'not',
'to',
'mention',
'tasty',
')',
'.'],
'aspect': ['scallops', 'black olive butter'],
'position': [[1, 7, 8, 9], [1, 7, 8, 9]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.15035274624824524, 0.0004513446183409542, 0.8491958379745483],
[0.0002442084369249642, 0.9990507960319519, 0.0007049772539176047]],
'confidence': [0.8491958379745483, 0.9990507960319519]},
{'sentence': 'my friend enjoyed the grilled alaskan king salmon with delectable creamed washington russet potatoes and crisp green beans .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['my',
'friend',
'enjoyed',
'the',
'grilled',
'alaskan',
'king',
'salmon',
'with',
'delectable',
'creamed',
'washington',
'russet',
'potatoes',
'and',
'crisp',
'green',
'beans',
'.'],
'aspect': ['salmon', 'beans'],
'position': [[7, 17], [7, 17]],
'sentiment': ['Neutral', 'Positive'],
'probs': [[0.00029835288296453655, 0.8501957654953003, 0.1495058387517929],
[0.000339262536726892, 0.0002576426195446402, 0.9994029998779297]],
'confidence': [0.8501957654953003, 0.9994029998779297]},
{'sentence': 'i had a taste of all three items on her plate , and they were superb .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['i',
'had',
'a',
'taste',
'of',
'all',
'three',
'items',
'on',
'her',
'plate',
',',
'and',
'they',
'were',
'superb',
'.'],
'aspect': ['plate'],
'position': [[10]],
'sentiment': ['Positive'],
'probs': [[0.00012904299364890903,
0.0018733675824478269,
0.9979975819587708]],
'confidence': [0.9979975819587708]},
{'sentence': "our server continued to be attentive throughout the night , but i did remain puzzled by one issue : who thinks that ray ' s is an appropriate place to take young children for dinner ?",
'IOB': ['O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O'],
'tokens': ['our',
'server',
'continued',
'to',
'be',
'attentive',
'throughout',
'the',
'night',
',',
'but',
'i',
'did',
'remain',
'puzzled',
'by',
'one',
'issue',
':',
'who',
'thinks',
'that',
'ray',
"'",
's',
'is',
'an',
'appropriate',
'place',
'to',
'take',
'young',
'children',
'for',
'dinner',
'?'],
'aspect': ['server', 'dinner'],
'position': [[1, 34], [1, 34]],
'sentiment': ['Positive', 'Neutral'],
'probs': [[0.0013677524402737617, 0.00017800692876335233, 0.998454213142395],
[0.0006732265464961529, 0.9989867806434631, 0.00034000579034909606]],
'confidence': [0.998454213142395, 0.9989867806434631]},
{'sentence': "all considered , i have to say that ray ' s boathouse is deserving of its title as a seattle institution .",
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'I-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['all',
'considered',
',',
'i',
'have',
'to',
'say',
'that',
'ray',
"'",
's',
'boathouse',
'is',
'deserving',
'of',
'its',
'title',
'as',
'a',
'seattle',
'institution',
'.'],
'aspect': ["ray '"],
'position': [[8, 9]],
'sentiment': ['Positive'],
'probs': [[0.0005467031733132899,
0.0002255972649436444,
0.9992276430130005]],
'confidence': [0.9992276430130005]},
{'sentence': 'while i could have done without the youth who shared the evening with us , our wonderful server and food made the experience a very positive one .',
'IOB': ['O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'B-ASP',
'O',
'B-ASP',
'O',
'O',
'O',
'O',
'O',
'O',
'O',
'O'],
'tokens': ['while',
'i',
'could',
'have',
'done',
'without',
'the',
'youth',
'who',
'shared',
'the',
'evening',
'with',
'us',
',',
'our',
'wonderful',
'server',
'and',
'food',
'made',
'the',
'experience',
'a',
'very',
'positive',
'one',
'.'],
'aspect': ['server', 'food'],
'position': [[17, 19], [17, 19]],
'sentiment': ['Positive', 'Positive'],
'probs': [[0.0003737751394510269, 0.0003592692955862731, 0.9992669224739075],
[0.00018869651830755174, 0.0006193331209942698, 0.99919193983078]],
'confidence': [0.9992669224739075, 0.99919193983078]}]
Annotate your own datasets based on PyABSA
Auto-Annotation # available for v1.0 currently Manually-Annotation
Deploy a ATEPC demo
Here is a simple web-based demo for aspect term extraction
[2]:
import os
import random
import gradio as gr
import pandas as pd
import requests
from pyabsa import (
download_all_available_datasets,
AspectTermExtraction as ATEPC,
TaskCodeOption,
)
from pyabsa.utils.data_utils.dataset_manager import detect_infer_dataset
download_all_available_datasets()
dataset_items = {dataset.name: dataset for dataset in ATEPC.ATEPCDatasetList()}
def get_example(dataset):
task = TaskCodeOption.Aspect_Polarity_Classification
dataset_file = detect_infer_dataset(dataset_items[dataset], task)
for fname in dataset_file:
lines = []
if isinstance(fname, str):
fname = [fname]
for f in fname:
print("loading: {}".format(f))
fin = open(f, "r", encoding="utf-8")
lines.extend(fin.readlines())
fin.close()
for i in range(len(lines)):
lines[i] = (
lines[i][: lines[i].find("$LABEL$")]
.replace("[B-ASP]", "")
.replace("[E-ASP]", "")
.strip()
)
return sorted(set(lines), key=lines.index)
dataset_dict = {
dataset.name: get_example(dataset.name) for dataset in ATEPC.ATEPCDatasetList()
}
aspect_extractor = ATEPC.AspectExtractor(checkpoint="multilingual")
def perform_inference(text, dataset):
if not text:
text = dataset_dict[dataset][random.randint(0, len(dataset_dict[dataset]) - 1)]
result = aspect_extractor.predict(text, pred_sentiment=True)
result = pd.DataFrame(
{
"aspect": result["aspect"],
"sentiment": result["sentiment"],
# 'probability': result[0]['probs'],
"confidence": [round(x, 4) for x in result["confidence"]],
"position": result["position"],
}
)
return result, "{}".format(text)
demo = gr.Blocks()
with demo:
gr.Markdown(
"# <p align='center'>Multilingual Aspect-based Sentiment Analysis !</p>"
)
output_dfs = []
with gr.Row():
with gr.Column():
input_sentence = gr.Textbox(
placeholder="Leave this box blank and choose a dataset will give you a random example...",
label="Example:",
)
gr.Markdown(
"You can find the datasets at [github.com/yangheng95/ABSADatasets](https://github.com/yangheng95/ABSADatasets/tree/v1.2/datasets/text_classification)"
)
dataset_ids = gr.Radio(
choices=[dataset.name for dataset in ATEPC.ATEPCDatasetList()[:-1]],
value="Laptop14",
label="Datasets",
)
inference_button = gr.Button("Let's go!")
gr.Markdown(
"There is a [demo](https://huggingface.co/spaces/yangheng/PyABSA-ATEPC-Chinese) specialized for the Chinese langauge"
)
gr.Markdown(
"This demo support many other language as well, you can try and explore the results of other languages by yourself."
)
with gr.Column():
output_text = gr.TextArea(label="Example:")
output_df = gr.DataFrame(label="Prediction Results:")
output_dfs.append(output_df)
inference_button.click(
fn=perform_inference,
inputs=[input_sentence, dataset_ids],
outputs=[output_df, output_text],
)
demo.launch()
[2023-02-14 00:56:56] (2.0.28) Datasets already exist in C:\Users\chuan\OneDrive - University of Exeter\AIProjects\PyABSA\examples-v2\aspect_term_extraction\integrated_datasets, skip download
[2023-02-14 00:56:56] (2.0.28) Try to load 113.Laptop14 dataset from local disk
loading: integrated_datasets\apc_datasets\110.SemEval\113.laptop14\Laptops_Test_Gold.xml.seg.inference
[2023-02-14 00:56:56] (2.0.28) Try to load 114.Restaurant14 dataset from local disk
loading: integrated_datasets\apc_datasets\110.SemEval\114.restaurant14\Restaurants_Test_Gold.xml.seg.inference
[2023-02-14 00:56:56] (2.0.28) Try to load 111.ARTS_Laptop14 dataset from local disk
loading: integrated_datasets\apc_datasets\110.SemEval\111.arts_laptop14\laptop_arts_test.dat.inference
[2023-02-14 00:56:56] (2.0.28) Try to load 112.ARTS_Restaurant14 dataset from local disk
loading: integrated_datasets\apc_datasets\110.SemEval\112.arts_restaurant14\rest_arts_test.dat.inference
[2023-02-14 00:56:56] (2.0.28) Try to load 115.Restaurant15 dataset from local disk
loading: integrated_datasets\apc_datasets\110.SemEval\115.restaurant15\restaurant_test.raw.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 116.Restaurant16 dataset from local disk
loading: integrated_datasets\apc_datasets\110.SemEval\116.restaurant16\restaurant_test.raw.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 101.ACL_Twitter dataset from local disk
FindFile Warning --> multiple targets ['integrated_datasets\\apc_datasets\\101.ACL_Twitter', 'integrated_datasets\\apc_datasets\\101.ACL_Twitter\\acl-14-short-data'] found, only return the shortest path: <integrated_datasets\apc_datasets\101.ACL_Twitter>
loading: integrated_datasets\apc_datasets\101.ACL_Twitter\acl-14-short-data\test.raw.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 109.MAMS dataset from local disk
loading: integrated_datasets\apc_datasets\109.MAMS\test.xml.dat.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 117.Television dataset from local disk
loading: integrated_datasets\apc_datasets\117.Television\Television_Test_Gold.xml.seg.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 118.TShirt dataset from local disk
loading: integrated_datasets\apc_datasets\118.TShirt\Menstshirt_Test_Gold.xml.seg.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 119.Yelp dataset from local disk
loading: integrated_datasets\apc_datasets\119.Yelp\yelp.test.txt.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 107.Phone dataset from local disk
loading: integrated_datasets\apc_datasets\102.Chinese\107.phone\phone.test.txt.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 104.Car dataset from local disk
loading: integrated_datasets\apc_datasets\102.Chinese\104.car\car.test.txt.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 106.Notebook dataset from local disk
loading: integrated_datasets\apc_datasets\102.Chinese\106.notebook\notebook.test.txt.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 103.Camera dataset from local disk
loading: integrated_datasets\apc_datasets\102.Chinese\103.camera\camera.test.txt.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 108.Shampoo dataset from local disk
loading: integrated_datasets\apc_datasets\102.Chinese\108.shampoo\hair.test.txt.inference
[2023-02-14 00:56:57] (2.0.28) Try to load 105.MOOC dataset from local disk
loading: integrated_datasets\apc_datasets\102.Chinese\105.mooc\mooc.test.txt.inference
[2023-02-14 00:56:58] (2.0.28) Try to load 121.MOOC_En dataset from local disk
loading: integrated_datasets\apc_datasets\121.MOOC_En\mooc-en.test.txt.inference
[2023-02-14 00:56:58] (2.0.28) Try to load 129.Kaggle dataset from local disk
loading: integrated_datasets\apc_datasets\129.Kaggle\test.csv.dat.inference
[2023-02-14 00:56:58] (2.0.28) Try to load 130.Chinese_Zhang dataset from local disk
loading: integrated_datasets\apc_datasets\130.Chinese_Zhang\test.txt.dat.apc.inference
[2023-02-14 00:56:58] (2.0.28) Try to load 107.Phone dataset from local disk
[2023-02-14 00:56:58] (2.0.28) Try to load 103.Camera dataset from local disk
[2023-02-14 00:56:58] (2.0.28) Try to load 106.Notebook dataset from local disk
[2023-02-14 00:56:58] (2.0.28) Try to load 104.Car dataset from local disk
[2023-02-14 00:56:58] (2.0.28) Please DO NOT mix datasets with different sentiment labels for trainer & inference !
loading: integrated_datasets\apc_datasets\102.Chinese\107.phone\phone.test.txt.inference
[2023-02-14 00:56:58] (2.0.28) Try to load 107.Phone dataset from local disk
[2023-02-14 00:56:58] (2.0.28) Try to load 103.Camera dataset from local disk
[2023-02-14 00:56:59] (2.0.28) Try to load 106.Notebook dataset from local disk
[2023-02-14 00:56:59] (2.0.28) Try to load 104.Car dataset from local disk
[2023-02-14 00:56:59] (2.0.28) Please DO NOT mix datasets with different sentiment labels for trainer & inference !
loading: integrated_datasets\apc_datasets\102.Chinese\107.phone\phone.test.txt.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 105.MOOC dataset from local disk
loading: integrated_datasets\apc_datasets\102.Chinese\105.mooc\mooc.test.txt.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 120.SemEval2016Task5 dataset from local disk
FindFile Warning --> multiple targets ['integrated_datasets\\apc_datasets\\120.SemEval2016Task5', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\122.arabic', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\123.dutch', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\124.english', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\125.french', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\126.russian', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\127.spanish', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\128.turkish'] found, only return the shortest path: <integrated_datasets\apc_datasets\120.SemEval2016Task5>
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\122.arabic\hotels_test_arabic.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 122.Arabic dataset from local disk
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\122.arabic\hotels_test_arabic.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 123.Dutch dataset from local disk
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\123.dutch\restaurants_test_dutch.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 127.Spanish dataset from local disk
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\127.spanish\restaurants_test_spanish.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 128.Turkish dataset from local disk
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\128.turkish\restaurants_test_turkish.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 126.Russian dataset from local disk
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\126.russian\restaurants_test_russian.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 125.French dataset from local disk
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\125.french\restaurants_test_french.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 124.English dataset from local disk
loading: integrated_datasets\apc_datasets\120.SemEval2016Task5\124.english\restaurants_test_english.xml.dat.inference
[2023-02-14 00:56:59] (2.0.28) Try to load 113.Laptop14 dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 114.Restaurant14 dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 116.Restaurant16 dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 101.ACL_Twitter dataset from local disk
FindFile Warning --> multiple targets ['integrated_datasets\\apc_datasets\\101.ACL_Twitter', 'integrated_datasets\\apc_datasets\\101.ACL_Twitter\\acl-14-short-data'] found, only return the shortest path: <integrated_datasets\apc_datasets\101.ACL_Twitter>
[2023-02-14 00:57:00] (2.0.28) Try to load 109.MAMS dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 117.Television dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 118.TShirt dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 119.Yelp dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 121.MOOC_En dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 129.Kaggle dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Please DO NOT mix datasets with different sentiment labels for trainer & inference !
loading: integrated_datasets\apc_datasets\110.SemEval\113.laptop14\Laptops_Test_Gold.xml.seg.inference
[2023-02-14 00:57:00] (2.0.28) Try to load 113.Laptop14 dataset from local disk
[2023-02-14 00:57:00] (2.0.28) Try to load 114.Restaurant14 dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 116.Restaurant16 dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Please DO NOT mix datasets with different sentiment labels for trainer & inference !
loading: integrated_datasets\apc_datasets\110.SemEval\113.laptop14\Laptops_Test_Gold.xml.seg.inference
[2023-02-14 00:57:01] (2.0.28) Try to load 114.Restaurant14 dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 116.Restaurant16 dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Please DO NOT mix datasets with different sentiment labels for trainer & inference !
loading: integrated_datasets\apc_datasets\110.SemEval\114.restaurant14\Restaurants_Test_Gold.xml.seg.inference
[2023-02-14 00:57:01] (2.0.28) Try to load 113.Laptop14 dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 114.Restaurant14 dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 116.Restaurant16 dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 101.ACL_Twitter dataset from local disk
FindFile Warning --> multiple targets ['integrated_datasets\\apc_datasets\\101.ACL_Twitter', 'integrated_datasets\\apc_datasets\\101.ACL_Twitter\\acl-14-short-data'] found, only return the shortest path: <integrated_datasets\apc_datasets\101.ACL_Twitter>
[2023-02-14 00:57:01] (2.0.28) Try to load 109.MAMS dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 117.Television dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 118.TShirt dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 119.Yelp dataset from local disk
[2023-02-14 00:57:01] (2.0.28) Try to load 107.Phone dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Try to load 103.Camera dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Try to load 106.Notebook dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Try to load 104.Car dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Try to load 105.MOOC dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Try to load 129.Kaggle dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Try to load 120.SemEval2016Task5 dataset from local disk
FindFile Warning --> multiple targets ['integrated_datasets\\apc_datasets\\120.SemEval2016Task5', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\122.arabic', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\123.dutch', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\124.english', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\125.french', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\126.russian', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\127.spanish', 'integrated_datasets\\apc_datasets\\120.SemEval2016Task5\\128.turkish'] found, only return the shortest path: <integrated_datasets\apc_datasets\120.SemEval2016Task5>
[2023-02-14 00:57:02] (2.0.28) Try to load 121.MOOC_En dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Try to load 130.Chinese_Zhang dataset from local disk
[2023-02-14 00:57:02] (2.0.28) Please DO NOT mix datasets with different sentiment labels for trainer & inference !
loading: integrated_datasets\apc_datasets\110.SemEval\113.laptop14\Laptops_Test_Gold.xml.seg.inference
[2023-02-14 00:57:02] (2.0.28) Load aspect extractor from checkpoints\ATEPC_MULTILINGUAL_CHECKPOINT
[2023-02-14 00:57:02] (2.0.28) config: checkpoints\ATEPC_MULTILINGUAL_CHECKPOINT\fast_lcf_atepc.config
[2023-02-14 00:57:02] (2.0.28) state_dict: checkpoints\ATEPC_MULTILINGUAL_CHECKPOINT\fast_lcf_atepc.state_dict
[2023-02-14 00:57:02] (2.0.28) model: None
[2023-02-14 00:57:02] (2.0.28) tokenizer: checkpoints\ATEPC_MULTILINGUAL_CHECKPOINT\fast_lcf_atepc.tokenizer
[2023-02-14 00:57:03] (2.0.28) Set Model Device: cuda:0
[2023-02-14 00:57:03] (2.0.28) Device Name: NVIDIA GeForce RTX 2080
Some weights of the model checkpoint at microsoft/mdeberta-v3-base were not used when initializing DebertaV2Model: ['mask_predictions.LayerNorm.weight', 'lm_predictions.lm_head.LayerNorm.weight', 'mask_predictions.LayerNorm.bias', 'lm_predictions.lm_head.dense.weight', 'mask_predictions.dense.weight', 'mask_predictions.classifier.bias', 'lm_predictions.lm_head.LayerNorm.bias', 'lm_predictions.lm_head.bias', 'lm_predictions.lm_head.dense.bias', 'mask_predictions.dense.bias', 'mask_predictions.classifier.weight']
- This IS expected if you are initializing DebertaV2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DebertaV2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
C:\Users\chuan\miniconda3\lib\site-packages\transformers\convert_slow_tokenizer.py:446: UserWarning: The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option which is not implemented in the fast tokenizers. In practice this means that the fast version of the tokenizer can produce unknown tokens whereas the sentencepiece version would have converted these unknown tokens into a sequence of byte tokens matching the original piece of text.
warnings.warn(
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
C:\Users\chuan\miniconda3\lib\site-packages\gradio\networking.py:57: ResourceWarning: unclosed <socket.socket fd=6248, family=AddressFamily.AF_INET, type=SocketKind.SOCK_STREAM, proto=0>
s = socket.socket() # create a socket object
ResourceWarning: Enable tracemalloc to get the object allocation traceback
C:\Users\chuan\miniconda3\lib\site-packages\gradio\networking.py:57: ResourceWarning: unclosed <socket.socket fd=5952, family=AddressFamily.AF_INET, type=SocketKind.SOCK_STREAM, proto=0>
s = socket.socket() # create a socket object
ResourceWarning: Enable tracemalloc to get the object allocation traceback
Running on local URL: http://127.0.0.1:7862
To create a public link, set `share=True` in `launch()`.
[2]:
C:\Users\chuan\AppData\Roaming\Python\Python310\site-packages\pyabsa\tasks\AspectTermExtraction\prediction\aspect_extractor.py:647: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
float(x) for x in F.softmax(i_apc_logits).cpu().numpy().tolist()
[2023-02-14 00:57:14] (2.0.28) The results of aspect term extraction have been saved in C:\Users\chuan\OneDrive - University of Exeter\AIProjects\PyABSA\examples-v2\aspect_term_extraction\Aspect Term Extraction and Polarity Classification.FAST_LCF_ATEPC.result.json
[2023-02-14 00:57:14] (2.0.28) Example 0: The only solution is to turn the <brightness:Neutral Confidence:0.8198688626289368> down , etc . .
C:\Users\chuan\AppData\Roaming\Python\Python310\site-packages\pyabsa\tasks\AspectTermExtraction\prediction\aspect_extractor.py:647: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
float(x) for x in F.softmax(i_apc_logits).cpu().numpy().tolist()
[2023-02-14 00:57:34] (2.0.28) The results of aspect term extraction have been saved in C:\Users\chuan\OneDrive - University of Exeter\AIProjects\PyABSA\examples-v2\aspect_term_extraction\Aspect Term Extraction and Polarity Classification.FAST_LCF_ATEPC.result.json
[2023-02-14 00:57:34] (2.0.28) Example 0: In fact I still use many Legacy <programs:Neutral Confidence:0.9923437237739563> - LRB - <Appleworks:Neutral Confidence:0.9929322004318237> , <FileMaker Pro:Neutral Confidence:0.9934661984443665> , <Quicken:Neutral Confidence:0.9928175210952759> , <Photoshop:Neutral Confidence:0.9908045530319214> etc - RRB - !
[ ]: