Precision Event Coreference Resolution Using Neural Network Classifiers

Abstract

This paper presents a neural network classifier approach to detecting both within-and crossdocument event coreference effectively using only event mention based features. Our approach does not (yet) rely on any event argument features such as semantic roles or spatiotemporal arguments. Experimental results on the ECB+ dataset show that our approach produces F 1 scores that significantly outperform the state-of-the-art methods for both within-document and cross-document event coreference resolution when we use B 3 and CEAF e evaluation measures, but gets worse F 1 score with the M U C measure. However, when we use the CoN LL measure, which is the average of these three scores, our approach has slightly better F 1 for withindocument event coreference resolution but is significantly better for cross-document event coreference resolution.

Sequential Cross-Document Coreference Resolution

“…This is largely due to the more complex nature of event mentions (i.e., a trigger and arguments) and their syntactic diversity (e.g., both verb phrases and noun-phrases). Prior work on event coreference typically involves pairwise scoring between mentions followed by a standard clustering algorithm to predict coreference links (Pandian et al, 2018;Choubey and Huang, 2017;Cremisini and Finlayson, 2020;Meged et al, 2020;Yu et al, 2020b;Cattan et al, 2020), classification over a fixed number of clusters (Kenyon-Dean et al, 2018) and template-based methods (Cybulska and Vossen, 2015b,a). While pairwise scoring (e.g., graphbased models, see §3.7) with clustering is effective, it requires tuned thresholds (for the clustering algorithm) and cannot use already predicted scores to inform later ones, since all scores are predicted independently.…”