Document-Level Relation Extraction with Relation Correlation Enhancement

TL;DR

This paper introduces a relation graph method that explicitly models and leverages relation correlations to improve document-level relation extraction, demonstrating enhanced performance when integrated with existing models.

Contribution

It proposes a novel relation graph approach with a re-weighting scheme and graph attention networks to explicitly exploit relation correlations in DocRE.

Findings

Improved multi-relation extraction performance.

Effective integration as a plug-and-play module.

Validation on experimental datasets shows significant gains.

Abstract

Document-level relation extraction (DocRE) is a task that focuses on identifying relations between entities within a document. However, existing DocRE models often overlook the correlation between relations and lack a quantitative analysis of relation correlations. To address this limitation and effectively capture relation correlations in DocRE, we propose a relation graph method, which aims to explicitly exploit the interdependency among relations. Firstly, we construct a relation graph that models relation correlations using statistical co-occurrence information derived from prior relation knowledge. Secondly, we employ a re-weighting scheme to create an effective relation correlation matrix to guide the propagation of relation information. Furthermore, we leverage graph attention networks to aggregate relation embeddings. Importantly, our method can be seamlessly integrated as a plug-and-play module into existing models. Experimental results demonstrate that our approach can enhance the performance of multi-relation extraction, highlighting the effectiveness of considering relation correlations in DocRE.