Graph Refinement for Coreference Resolution
Lesly Miculicich, James Henderson · Findings of the Association for Computational Linguistics: ACL 2022 · 2022
The state-of-the-art models for coreference resolution are based on independent mention pairwise decisions.We propose a modelling approach that learns coreference at the documentlevel and takes global decisions.For this purpose, we model coreference links in a graph structure where the nodes are tokens in the text, and the edges represent the relationship between them.Our model predicts the graph in a non-autoregressive manner, then iteratively refines it based on previous predictions, allowing global dependencies between decisions.The experimental results show improvements over various baselines, reinforcing the hypothesis that document-level information improves conference resolution.