Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference

EMNLP 2021  ·  William Held, Dan Iter, Dan Jurafsky ·

Performing event and entity coreference resolution across documents vastly increases the number of candidate mentions, making it intractable to do the full $n^2$ pairwise comparisons. Existing approaches simplify by considering coreference only within document clusters, but this fails to handle inter-cluster coreference, common in many applications. As a result cross-document coreference algorithms are rarely applied to downstream tasks. We draw on an insight from discourse coherence theory: potential coreferences are constrained by the reader's discourse focus. We model the entities/events in a reader's focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters. We then use these neighborhoods to sample only hard negatives to train a fine-grained classifier on mention pairs and their local discourse features. Our approach achieves state-of-the-art results for both events and entities on the ECB+, Gun Violence, Football Coreference, and Cross-Domain Cross-Document Coreference corpora. Furthermore, training on multiple corpora improves average performance across all datasets by 17.2 F1 points, leading to a robust coreference resolution model for use in downstream tasks where link distribution is unknown.

PDF Abstract EMNLP 2021 PDF EMNLP 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Event Cross-Document Coreference Resolution ECB+ test Held et al CoNLL F1 85.7 # 1
Entity Cross-Document Coreference Resolution ECB+ test Held et al CoNLL F1 82.0 # 2
Event Coreference Resolution Gun Violence Corpus Held et al. B3 83.0 # 1

Methods


No methods listed for this paper. Add relevant methods here