Pairwise Cross-Document Event Coreference Resolution with Contrastive Learning

Abstract

Cross-Document (CD) Event Coreference Resolution (ECR) is a fundamental task in Natural Language processing (NLP) and Knowledge Base Population (KBP). Resolving the event coreference relationship is a challenging task, which necessitates a thorough semantic comprehension of the events. Existing methods have spontaneously formulated this problem as a binary classification task based on sentence segments. However, the information distributed in the longer context is ignored by most prior works. Recent event coreference works focus on adding auxiliary information to improve the performance. The information such as involved entity information, structural information or database queried information is extracted from related documents as long context. Whereas extraction error, matching error and other types of error are introduced in the process of obtaining related information when the context is incomplete. In this work, we present a Contrastive Learning based Pairwise Event Coreference (CLPEC) framework to complete and optimize the CD-ECR task utilizing contextual information with contrastive learning technology. We also adopt augmentation technology to preprocess event representations and improve our performance. Experiment results show that we achieve competitive results on a number of key metrics on the ECB+ corpus.