An End-to-End Approach for Full Bridging Resolution - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

An End-to-End Approach for Full Bridging Resolution

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.
Fichier principal
Vignette du fichier
2021.codi-sharedtask.5.pdf (279.41 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

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

Licence

Attribution

Identifiers

  • HAL Id : hal-03431313 , version 1

Cite

Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, Pascal Denis. An End-to-End Approach for Full Bridging Resolution. CODI-CRAC 2021 - Shared-Task: Anaphora Resolution in Dialogues, Nov 2021, Punta Cana, Dominican Republic. pp.48-54. ⟨hal-03431313⟩
70 View
80 Download

Share

Gmail Facebook X LinkedIn More