frankniujc / tdg-discourse

Code, data, and results of CODI 2023 paper Discourse Information for Document-Level Temporal Dependency Parsing

TDG Discourse

Code, data, and results of CODI 2023 paper Discourse Information for Document-Level Temporal Dependency Parsing.

Quick Start

After installing all the required packages in requirements.txt, you can start the training process by:

python cli.py --relation-type t2t -ma spe

See more information, call python cli.py --help.

Citation

@inproceedings{niu-etal-2023-discourse,
    title = "Discourse Information for Document-Level Temporal Dependency Parsing",
    author = "Niu, Jingcheng  and
      Ng, Victoria  and
      Rees, Erin  and
      De Montigny, Simon  and
      Penn, Gerald",
    booktitle = "Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.codi-1.10",
    pages = "82--88",
}