Event Detection as Graph Parsing

Abstract

Event detection is a fundamental task in information extraction. Most previous approaches typically view event detection as a trigger-based classification problem, focusing on using syntactic dependency structure or external knowledge to boost the classification performance. To overcome the inherent issues with existing trigger classification based models, we propose a novel approach to event detection by formulating it as a graph parsing problem, which can explicitly model the multiple event correlations and naturally utilize the rich information conveyed by event type and subtype. Furthermore, to cope with data sparsity, we employ a pretrained sequence-to-sequence (seq2seq) model to transduce an input sentence into an accurate event graph without the need for trigger words. Extensive experimental results on the public ACE2005 dataset show that, our approach outperforms all previous state-of-the-art models for event detection by a large margin, obtaining an improvement of 4.2% F1 score. The result is very encouraging since we achieve this with a conceptually simple seq2seq model; moreover, by extending the graph structure, this proposed architecture can be flexibly applied to more information extraction problems for sentences.