Home

Awesome

SRL-MM

This is the implementation of Syntax-driven Approach for Semantic Role Labeling at LREC2022.

Please contact us at yhtian@uw.edu if you have any questions.

Citation

If you use or extend our work, please cite our paper at LREC2022.

@InProceedings{tian-EtAl:2022:LREC2,
  author = {Tian, Yuanhe and Qin, Han and Xia, Fei and  Song, Yan},
  title = {Syntax-driven Approach for Semantic Role Labeling},
  booktitle = {Proceedings of the Language Resources and Evaluation Conference},
  month = {June},
  year = {2022},
  address = {Marseille, France},
  pages = {7129--7139},
}

Requirements

Our code works with the following environment.

Downloading BERT and XLNet

In our paper, we use BERT and XLNet as the encoder. We follow the instructions to convert the TensorFlow checkpoints to the PyTorch version.

Note: for XLNet, it is possible that the resulting config.json misses the hyper-parameter n_token. You can manually add it and set its value to 32000 (which is identical to vocab_size).

Datasets

We use CoNLL 2005 and CoNLL 2012 in our paper.

To obtain and pre-process the data, please go to data_processing directory for more information.

All processed data will appear in data directory.

Train and Test the model

You can find the command lines to train and test models on a small sample data in run_sample.sh.

Here are some important parameters: