Publikation
Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task)
Tatiana Anikina; Natalia Skachkova; Joseph Renner; Priyansh Trivedi
In: Juntao Yu; Sopan Khosla; Ramesh Manuvinakurike; Lori Levin; Vincent Ng; Massimo Poesio; Michael Strube; Carolyn Rose (Hrsg.). Proceedings of the CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue. Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC-2022), located at COLING, October 16-17, Gyeongju, Korea, Republic of, Pages 15-27, Association for Computational Linguistics, 10/2022.
Zusammenfassung
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.
Projekte
- IMPRESS - Verbesserte Wort- und Satzeinbettung mithilfe semantischen Wissens
- CORA4NLP - Ko(n)textuelles Schließen und Anpassung an den Kontext bei der Verarbeitung natürlicher Sprache