Reconstructing Event Regions for Event Extraction via Graph Attention Networks

Pei Chen1, Hang Yang2, Kang Liu2, Ruihong Huang1, Yubo Chen2, Taifeng Wang3, Jun Zhao4
1Texas A&M University, 2Institute of Automation, Chinese Academy of Sciences, 3Ant Finance, 4Chinese Academy of Sciences


Event information is usually scattered across multiple sentences within a document. The local sentence-level event extractors often yield many noisy event role filler extractions in the absence of a broader view of the document-level context. Filtering spurious extractions and aggregating event information in a document remains a challenging problem. Following the observation that a document has several relevant event regions densely populated with event role fillers, we build graphs with candidate role filler extractions enriched by sentential embeddings as nodes, and use graph attention networks to identify event regions in a document and aggregate event information. We characterize edges between candidate extractions in a graph into rich vector representations to facilitate event region identification. The experimental results on two datasets of two languages show that our approach yields new state-of-the-art performance for the challenging event extraction task.