An End-to-End Approach for Full Bridging Resolution - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

An End-to-End Approach for Full Bridging Resolution

Résumé

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.
Fichier principal
Vignette du fichier
2021.codi-sharedtask.5.pdf (279.41 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03431313 , version 1 (16-11-2021)

Licence

Identifiants

Citer

Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, Pascal Denis. An End-to-End Approach for Full Bridging Resolution. Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue, Nov 2021, Punta Cana, Dominican Republic. pp.48-54, ⟨10.18653/v1/2021.codi-sharedtask.5⟩. ⟨hal-03431313⟩
78 Consultations
94 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More