Within-Document Event Coreference with BERT-Based Contextualized Representations

arXiv:2102.09600v2 Announce Type: replace
Abstract: Event coreference continues to be a challenging problem in information extraction. With the absence of any external knowledge bases for events, coreference becomes a clustering task that relies on effective representations of the context in which event mentions appear. Recent advances in contextualized language representations have proven successful in many tasks, however, their use in event linking been limited. Here we present a three part approach that (1) uses representations derived from a pretrained BERT …

abstract advances arxiv bert clustering context cs.ai cs.cl cs.ir document event events extraction information information extraction knowledge language type