Document-level relation extraction via commonsense knowledge enhanced graph representation learning

Qizhu Dai

doi:10.1007/s10489-024-05985-y

Return

Document-level relation extraction via commonsense knowledge enhanced graph representation learning

2024-12-14

PRE

DOI：10.1007/s10489-024-05985-y

Original

Original request for help

Save

Abstract

En 中文

Document-level relation extraction (DocRE) aims to reason about complex relational facts among entities by reading, inferring, and aggregating among entities over multiple sentences in a document. Existing studies construct document-level graphs to enrich interactions between entities. However, these methods pay more attention to the entity nodes and their connections, regardless of the rich knowledge entailed in the original corpus.In this paper, we propose a commonsense knowledge enhanced document-level graph representation, called CGDRE, which delves into the semantic knowledge of the original corpus and improves the ability of DocRE. Firstly, we use coreference contrastive learning to capture potential commonsense knowledge. Secondly, we construct a heterogeneous graph to enhance the graph structure information according to the original document and commonsense knowledge. Lastly, CGDRE infers relations on the aggregated graph and uses focal loss to train the model. Remarkably, it is amazing that CGDRE can effectively alleviate the long-tailed distribution problem in DocRE. Experiments on the public datasets DocRED, DialogRE, and MPDD show that CGDRE can significantly outperform other baselines, achieving a significant performance improvement. Extensive analyses demonstrate that the performance of our CGDRE is contributed by the capture of commonsense knowledge enhanced graph relation representation.

Keywords:

Document-level relation extraction

Contrastive learning

Commonsense knowledge

Graph neural network