Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task)

Tatiana Anikina, Natalia Skachkova, Joseph Renner, Priyansh Trivedi


Abstract
We describe three models submitted for the CODI-CRAC 2022 shared task. To perform identity anaphora resolution, we test several combinations of the incremental clustering approach based on the Workspace Coreference System (WCS) with other coreference models. The best result is achieved by adding the “cluster merging” version of the coref-hoi model, which brings up to 10.33% improvement1 over vanilla WCS clustering. Discourse deixis resolution is implemented as multi-task learning: we combine the learning objective of coref-hoi with anaphor type classification. We adapt the higher-order resolution model introduced in Joshi et al. (2019) for bridging resolution given gold mentions and anaphors.
Anthology ID:
2022.codi-crac.2
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:
15–27
Language:
URL:
https://aclanthology.org/2022.codi-crac.2
DOI:
Bibkey:
Cite (ACL):
Tatiana Anikina, Natalia Skachkova, Joseph Renner, and Priyansh Trivedi. 2022. Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task). In Proceedings of the CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue, pages 15–27, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task) (Anikina et al., CODI 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.codi-crac.2.pdf
Data
BASHICoNLL-2012ISNotes