Query-based Instance Discrimination Network for Relational Triple Extraction

TL;DR

This paper introduces a query-based, contrastive learning approach for relational triple extraction that reduces error propagation and captures high-level connections, achieving state-of-the-art results.

Contribution

It proposes a novel query-based method with metric comparison and contrastive learning to improve relational triple extraction accuracy and global connection modeling.

Findings

Achieves state-of-the-art performance on five benchmarks.

Effectively reduces error propagation in triple extraction.

Captures high-order global connections between triples.

Abstract

Joint entity and relation extraction has been a core task in the field of information extraction. Recent approaches usually consider the extraction of relational triples from a stereoscopic perspective, either learning a relation-specific tagger or separate classifiers for each relation type. However, they still suffer from error propagation, relation redundancy and lack of high-level connections between triples. To address these issues, we propose a novel query-based approach to construct instance-level representations for relational triples. By metric-based comparison between query embeddings and token embeddings, we can extract all types of triples in one step, thus eliminating the error propagation problem. In addition, we learn the instance-level representation of relational triples via contrastive learning. In this way, relational triples can not only enclose rich class-level semantics but also access to high-order global connections. Experimental results show that our proposed method achieves the state of the art on five widely used benchmarks.