Separately Parameterizing Singleton Detection Improves End-to-end Neural Coreference Resolution

Xiyuan Zou, Yiran Li, Ian Porada, Jackie C. K. Cheung

Abstract: Current end-to-end coreference resolution models combine detection of singleton mentions and antecedent linking into a single step. In contrast, singleton detection was often treated as a separate step in the pre-neural era. In this work, we show that separately parameterizing these two sub-tasks also benefits end-to-end neural coreference systems. Specifically, we add a singleton detector to the coarse-to-fine (C2F) coreference model, and design an anaphoricity-aware span embedding and singleton detection loss. Our method significantly improves model performance on OntoNotes and four additional datasets.

External IDs:dblp:conf/naacl/ZouLPC24