Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation
This work addresses event detection for information extraction, offering an incremental improvement by better utilizing linguistic knowledge.
The paper tackles event detection in text by proposing Edge-Enhanced Graph Convolution Networks (EE-GCN), which integrate both syntactic structure and dependency label information, resulting in significant improvement over baseline methods on the ACE2005 dataset.
Event detection (ED), a key subtask of information extraction, aims to recognize instances of specific event types in text. Previous studies on the task have verified the effectiveness of integrating syntactic dependency into graph convolutional networks. However, these methods usually ignore dependency label information, which conveys rich and useful linguistic knowledge for ED. In this paper, we propose a novel architecture named Edge-Enhanced Graph Convolution Networks (EE-GCN), which simultaneously exploits syntactic structure and typed dependency label information to perform ED. Specifically, an edge-aware node update module is designed to generate expressive word representations by aggregating syntactically-connected words through specific dependency types. Furthermore, to fully explore clues hidden in dependency edges, a node-aware edge update module is introduced, which refines the relation representations with contextual information. These two modules are complementary to each other and work in a mutual promotion way. We conduct experiments on the widely used ACE2005 dataset and the results show significant improvement over competitive baseline methods.