Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues

Liyan Xu, Jinho D. Choi


Abstract
We present an effective system adapted from the end-to-end neural coreference resolution model, targeting on the task of anaphora resolution in dialogues. Three aspects are specifically addressed in our approach, including the support of singletons, encoding speakers and turns throughout dialogue interactions, and knowledge transfer utilizing existing resources. Despite the simplicity of our adaptation strategies, they are shown to bring significant impact to the final performance, with up to 27 F1 improvement over the baseline. Our final system ranks the 1st place on the leaderboard of the anaphora resolution track in the CRAC 2021 shared task, and achieves the best evaluation results on all four datasets.
Anthology ID:
2021.codi-sharedtask.6
Volume:
Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Sopan Khosla, Ramesh Manuvinakurike, Vincent Ng, Massimo Poesio, Michael Strube, Carolyn Rosé
Venue:
CODI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
55–62
Language:
URL:
https://aclanthology.org/2021.codi-sharedtask.6
DOI:
10.18653/v1/2021.codi-sharedtask.6
Bibkey:
Cite (ACL):
Liyan Xu and Jinho D. Choi. 2021. Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues. In Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue, pages 55–62, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues (Xu & Choi, CODI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.codi-sharedtask.6.pdf