Graph Refinement for Coreference Resolution
Lesly Miculicich, James Henderson
2022Findings of the Association for Computational Linguistics: ACL 202210 citationsDOIOpen Access PDF
Abstract
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.
Topics & Concepts
CoreferenceComputer scienceGraphResolution (logic)Artificial intelligenceNatural language processingMachine learningData miningTheoretical computer scienceTopic ModelingAdvanced Graph Neural NetworksSemantic Web and Ontologies