An End-to-End Approach for Full Bridging Resolution

Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, Pascal Denis


Abstract
In this article, we describe our submission to the CODI-CRAC 2021 Shared Task on Anaphora Resolution in Dialogues – Track BR (Gold). We demonstrate the performance of an end-to-end transformer-based higher-order coreference model finetuned for the task of full bridging. We find that while our approach is not effective at modeling the complexities of the task, it performs well on bridging resolution, suggesting a need for investigations into a robust anaphor identification model for future improvements.
Anthology ID:
2021.codi-sharedtask.5
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:
48–54
Language:
URL:
https://aclanthology.org/2021.codi-sharedtask.5
DOI:
10.18653/v1/2021.codi-sharedtask.5
Bibkey:
Cite (ACL):
Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, and Pascal Denis. 2021. An End-to-End Approach for Full Bridging Resolution. In Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue, pages 48–54, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
An End-to-End Approach for Full Bridging Resolution (Renner et al., CODI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.codi-sharedtask.5.pdf