Constrained Multi-Task Learning for Bridging Resolution

Hideo Kobayashi; Yufang Hou; Vincent Ng

ACL 2022long8 citations

Constrained Multi-Task Learning for Bridging Resolution

Abstract

We examine the extent to which supervised bridging resolvers can be improved without employing additional labeled bridging data by proposing a novel constrained multi-task learning framework for bridging resolution, within which we (1) design cross-task consistency constraints to guide the learning process; (2) pre-train the entity coreference model in the multi-task framework on the large amount of publicly available coreference data; and (3) integrating prior knowledge encoded in rule-based resolvers. Our approach achieves state-of-the-art results on three standard evaluation corpora.

BibTeX

@inproceedings{kobayashi-etal-2022-constrained,
    title = "Constrained Multi-Task Learning for Bridging Resolution",
    author = "Kobayashi, Hideo  and
      Hou, Yufang  and
      Ng, Vincent",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.56/",
    doi = "10.18653/v1/2022.acl-long.56",
    pages = "759--770"
}