Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks
Preprint
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 ($\hgnn{}$), 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 (\acef{}, \ace{} and \scierc{}) for ERE task show significant improvements over the previous state-of-the-art PL-marker.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Graph Neural Networks Meet Probabilistic Graphical Models: A Survey2025
- HGNN+: General Hypergraph Neural NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Hypergraph convolution and hypergraph attentionPattern Recognition, 2021
- A Partition Filter Network for Joint Entity and Relation Extraction2021
- UniRE: A Unified Label Space for Entity Relation Extraction2021
- High-order Semantic Role Labeling2020
- Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders2020
- Denoising Relation Extraction from Document-level Distant Supervision2020
- Efficient Second-Order TreeCRF for Neural Dependency Parsing2020
- Conditional Random Fields as Recurrent Neural Networks2015