Abstract
While Yu and Poesio (2020) have recently demonstrated the superiority of their neural multi-task learning (MTL) model to rule-based approaches for bridging anaphora resolution, there is little understanding of (1) how it is better than the rule-based approaches (e.g., are the two approaches making similar or complementary mistakes?) and (2) what should be improved. To shed light on these issues, we (1) propose a hybrid rule-based and MTL approach that would enable a better understanding of their comparative strengths and weaknesses; and (2) perform a manual analysis of the errors made by the MTL model.- Anthology ID:
- 2021.naacl-main.131
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1652–1659
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.131
- DOI:
- 10.18653/v1/2021.naacl-main.131
- Cite (ACL):
- Hideo Kobayashi and Vincent Ng. 2021. Bridging Resolution: Making Sense of the State of the Art. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1652–1659, Online. Association for Computational Linguistics.
- Cite (Informal):
- Bridging Resolution: Making Sense of the State of the Art (Kobayashi & Ng, NAACL 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.naacl-main.131.pdf
- Data
- ISNotes