Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks

Zhaohui Yan, Songlin Yang, Wei Liu, Kewei Tu

Submission Type: Regular Long Paper

Submission Track: Information Extraction

Keywords: Entity and Relation Extraction, high-order inference, hypergraph neural network

TL;DR: This article proposes a novel joint Entity and Relation Extraction model, which employs hypergraph neural network for higher-order modeling and outperforms the previous state-of-the-art.

Abstract: Entity and Relation Extraction (ERE) is an important task in information extraction. Recent marker-based pipeline models achieve state-of-the-art performance, but still suffer from the error propagation issue. Also, most of current ERE models do not take into account higher-order interactions between multiple entities and relations, while higher-order modeling could be beneficial.In this work, we propose HyperGraph neural network for ERE (HGERE), which is built upon the PL-marker (a state-of-the-art marker-based pipleline model). To alleviate error propagation, we use a high-recall pruner mechanism to transfer the burden of entity identification and labeling from the NER module to the joint module of our model. For higher-order modeling, we build a hypergraph, where nodes are entities (provided by the span pruner) and relations thereof, and hyperedges encode interactions between two different relations or between a relation and its associated subject and object entities. We then run a hypergraph neural network for higher-order inference by applying message passing over the built hypergraph. Experiments on three widely used benchmarks (ACE2004, ACE2005 and SciERC) for ERE task show significant improvements over the previous state-of-the-art PL-marker.

Submission Number: 4093