Citing PyABSA

If you use PyABSA in your research or commercial projects, please cite our work. Your citation is a valuable acknowledgment of our efforts and supports the continued development of the framework.

Main Framework Citation

For general use of the PyABSA framework, please cite our main paper:

@misc{yang2023pyabsa,
    title = {PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis},
    author = {Heng Yang and Ke Li},
    year = {2023},
    eprint = {2208.01368},
    archivePrefix = {arXiv},
    primaryClass = {cs.CL}
}

Model-Specific Citations

PyABSA integrates state-of-the-art models from various research papers. If you use a specific model, we encourage you to cite the original paper to give due credit to the researchers who developed it.

Aspect Polarity Classification Models

Fast-LSA Series

@article{Yang2021FastLSA,
    title = {Back to Reality: Leveraging Pattern-driven Modeling to Enable Affordable Sentiment Dependency Learning},
    author = {Yang, Heng and Zeng, Biqing and Yang, Jianhao and Song, Youwei and Xu, Ruyang},
    journal = {arXiv preprint arXiv:2110.08604},
    year = {2021},
    url = {https://arxiv.org/abs/2110.08604}
}

LCF-BERT

@inproceedings{zeng-etal-2019-lcf,
    title = "{LCF}: A Local Context Focus Mechanism for Aspect-Based Sentiment Classification",
    author = "Zeng, Biqing  and
      Yang, Heng  and
      Xu, Ruyang  and
      Song, Youwei  and
      Zha, Zhaopeng",
    booktitle = "Proceedings of the 2019 International Conference on Natural Language Processing and Chinese Computing",
    month = oct,
    year = "2019",
    address = "Dunhuang, China",
    publisher = "Springer",
    url = "https://aclanthology.org/2019.nlcc-1.1",
    pages = "1--13"
}

Aspect Term Extraction Models

T-SCSA

@article{zeng2019scsa,
    title = {SCSA: A novel supervised and clustering-based sentiment analysis method for aspect-level and sentence-level texts},
    author = {Zeng, Biqing and Yang, Heng and Song, Youwei and Xu, Ruyang and Zha, Zhaopeng},
    journal = {IEEE Access},
    volume = {7},
    pages = {175034--175044},
    year = {2019},
    publisher = {IEEE}
}

We appreciate your support in acknowledging the work that makes PyABSA possible.