Weakly- and Semi-supervised Evidence Extraction

Code and datasets for the following paper:

Weakly- and Semi-supervised Evidence Extraction

Danish Pruthi, Bhuwan Dhingra, Graham Neubig, and Zachary C. Lipton

Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2020)

Setup instructions

For dependencies, please check the environment.yml file. To create the same conda environment you can run conda env create -f environment.yml (You might have to edit the prefix in the last line in the file.)

Further

cd src
git clone https://github.com/danishpruthi/transformers-local

Reference

If you use the code or ideas from the paper, please consider citing the paper using the following bibTex:

@inproceedings{pruthi-etal-2020-weakly,
    title = "Weakly- and Semi-supervised Evidence Extraction",
    author = "Pruthi, Danish  and
      Dhingra, Bhuwan  and
      Neubig, Graham  and
      Lipton, Zachary C.",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.findings-emnlp.353",
    doi = "10.18653/v1/2020.findings-emnlp.353",
    pages = "3965--3970",
}