kayoyin / scr

Signed Coreference Resolution (EMNLP 2021)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Signed Coreference Resolution

This repository gathers the code, data and annotation interface for Signed Coreference Resolution

To run the multigraph model:

    python run-multigraph.py -in dgs-coref/data.json -out multigraph.out 

To evaluate the outputs:

    python format_conll.py --data dgs-coref/data.json --key >  multigraph.key
    python format_conll.py --data  multigraph.out >  multigraph.answer
    perl scorer.pl all multigraph.key  multigraph.answer >  multigraph.score

Please cite the paper below if you found the resources in this repository useful:

@inproceedings{yin-etal-2021-signed,
    title = "Signed Coreference Resolution",
    author = "Yin, Kayo  and
      DeHaan, Kenneth  and
      Alikhani, Malihe",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-main.405",
    pages = "4950--4961",
}

About

Signed Coreference Resolution (EMNLP 2021)

License:BSD 3-Clause "New" or "Revised" License


Languages

Language:Python 56.7%Language:HTML 42.2%Language:Perl 1.1%