vix.ing · top · new · best · stats · spec

Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues

2021/09/01 by Liyan Xu, Jinho D. Choi, Xu, Liyan +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2109.00185

openalex publication_date 2021/09/01 · openalex created_date 2021/11/22 · openalex updated_date 2026/07/28

Abstract

We present an effective system adapted from the end-to-end neural coreference resolution model, targeting on the task of anaphora resolution in dialogues. Three aspects are specifically addressed in our approach, including the support of singletons, encoding speakers and turns throughout dialogue interactions, and knowledge transfer utilizing existing resources. Despite the simplicity of our adaptation strategies, they are shown to bring significant impact to the final performance, with up to 27 F1 improvement over the baseline. Our final system ranks the 1st place on the leaderboard of the anaphora resolution track in the CRAC 2021 shared task, and achieves the best evaluation results on all four datasets.

Related