Skip to content

Latest commit

 

History

History
57 lines (34 loc) · 2.07 KB

README.md

File metadata and controls

57 lines (34 loc) · 2.07 KB
Raw

ASA-WD

This is the implementation of Enhancing Aspect-level Sentiment Analysis with Word Dependencies at EACL 2021.

You can e-mail Yuanhe Tian at yhtian@uw.edu if you have any questions.

Citation

If you use or extend our work, please cite our paper at EACL 2021.

@inproceedings{tian-etal-2021-enhancing,
    title = "Enhancing Aspect-level Sentiment Analysis with Word Dependencies",
    author = "Tian, Yuanhe  and Chen, Guimin  and Song, Yan",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    year = "2021",
}

Requirements

Our code works with the following environment.

  • python=3.7
  • pytorch=1.3

Dataset

To obtain the data, you can go to data directory for details.

Downloading BERT and ASA-WD

In our paper, we use BERT (paper) as the encoder.

For BERT, please download pre-trained BERT-Base and BERT-Large English from Google or from HuggingFace. If you download it from Google, you need to convert the model from TensorFlow version to PyTorch version.

For ASA-WD, you can download the models we trained in our experiments from Google Drive or Baidu Net Disk (passwword: ga1w).

Run on Sample Data

Run run_sample.sh to train a model on the small sample data under the sample_data directory.

Training and Testing

You can find the command lines to train and test models in run_train.sh and run_test.sh, respectively.

Here are some important parameters:

  • --do_train: train the model.
  • --do_eval: test the model.

To-do List

  • Release the code to get the data.
  • Regular maintenance.

You can leave comments in the Issues section, if you want us to implement any functions.