HyperMatch

This repository provides the code of the paper Hyperbolic Relevance Matching for Neural Keyphrase Extraction (NAACL2022).

The predicted results are here.

When using, you only need to copy the code of the HyperMatch model in the associated file (defined in networks/HyperMatch.py) to another file (networks/Roberta2Rank.py). Then train the model according to the corresponding script.

Please cite our paper if our experimental results, analysis conclusions or the code are helpful to you ~ 😊

@inproceedings{DBLP:conf/naacl/SongFJ22,
  author    = {Mingyang Song and
               Yi Feng and
               Liping Jing},
  editor    = {Marine Carpuat and
               Marie{-}Catherine de Marneffe and
               Iv{\'{a}}n Vladimir Meza Ru{\'{\i}}z},
  title     = {Hyperbolic Relevance Matching for Neural Keyphrase Extraction},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of
               the Association for Computational Linguistics: Human Language Technologies,
               {NAACL} 2022, Seattle, WA, United States, July 10-15, 2022},
  pages     = {5710--5720},
  publisher = {Association for Computational Linguistics},
  year      = {2022},
  url       = {https://doi.org/10.18653/v1/2022.naacl-main.419},
  doi       = {10.18653/v1/2022.naacl-main.419},
  timestamp = {Mon, 01 Aug 2022 16:28:03 +0200},
  biburl    = {https://dblp.org/rec/conf/naacl/SongFJ22.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

CONTACT

For any question, feel free to create an issue, and we will try our best to solve.
If the problem is more urgent, you can send an email to me at the same time (I check email almost everyday 😉).

NAME: Mingyang Song
EMAIL: mingyang.song@bjtu.edu.cn

Our implementation is built on the source code from BERT-KPE. Thanks for their work.