PPAT: Progressive Graph Pairwise Attention Network for Event Causality Identification

zhenyu liu, Zhenran Xu, Baotian Hu

Keywords: Event causality identification, graph neural network, natural language processing

Abstract: Event Causality Identification (ECI) aims to identify the causality between a pair of event mentions in a document, which is composed of sentence-level ECI (SECI) and document-level ECI (DECI). Previous work applies various reasoning models to help identify the implicit event causality. However, they ignore that most inter-sentence event causality depends on intra-sentence event causality to infer. In this paper, we propose a progressive graph pairwise attention network (PPAT) to consider the above dependence. PPAT applies a progressive reasoning strategy, as it first predicts the intra-sentence causality, and then infers the more implicit inter-sentence causality based on the SECI result. We construct a sentence boundary event relational graph, and PPAT leverages a novel pairwise attention, which attends to different reasoning chains on the graph. In addition, we propose a causality-guided training strategy for assisting PPAT in learning causality-related representations on every layer. Extensive experiments on two well-established benchmark datasets show that our model achieves state-of-the-art performance (5.5% F1 gains on EventStoryLine and 4.5% F1 gains on Causal-TimeBank).

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

TL;DR: We propose PPAT for event causality identification, which reasons inter-sentence event causality based on intra-sentence event causality and outperforms all previous methods.