Pipeline Coreference Resolution Model for Anaphoric Identity in Dialogues

Damrin Kim, Seongsik Park, Mirae Han, Harksoo Kim


Abstract
CODI-CRAC 2022 Shared Task in Dialogues consists of three sub-tasks: Sub-task 1 is the resolution of anaphoric identity, sub-task 2 is the resolution of bridging references, and sub-task 3 is the resolution of discourse deixis/abstract anaphora. Anaphora resolution is the task of detecting mentions from input documents and clustering the mentions of the same entity. The end-to-end model proceeds with the pruning of the candidate mention, and the pruning has the possibility of removing the correct mention. Also, the end-to-end anaphora resolution model has high model complexity, which takes a long time to train. Therefore, we proceed with the anaphora resolution as a two-stage pipeline model. In the first mention detection step, the score of the candidate word span is calculated, and the mention is predicted without pruning. In the second anaphora resolution step, the pair of mentions of the anaphora resolution relationship is predicted using the mentions predicted in the mention detection step. We propose a two-stage anaphora resolution pipeline model that reduces model complexity and training time, and maintains similar performance to end-to-end models. As a result of the experiment, the anaphora resolution showed a performance of 68.27% in Light, 48.87% in AMI, 69.06% in Persuasion, and 60.99% on Switchboard. Our final system ranked 3rd on the leaderboard of sub-task 1.
Anthology ID:
2022.codi-crac.3
Volume:
Proceedings of the CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Juntao Yu, Sopan Khosla, Ramesh Manuvinakurike, Lori Levin, Vincent Ng, Massimo Poesio, Michael Strube, Carolyn Rose
Venue:
CODI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
28–31
Language:
URL:
https://aclanthology.org/2022.codi-crac.3
DOI:
Bibkey:
Cite (ACL):
Damrin Kim, Seongsik Park, Mirae Han, and Harksoo Kim. 2022. Pipeline Coreference Resolution Model for Anaphoric Identity in Dialogues. In Proceedings of the CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue, pages 28–31, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Pipeline Coreference Resolution Model for Anaphoric Identity in Dialogues (Kim et al., CODI 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.codi-crac.3.pdf