GEGA: Graph Convolutional Networks and Evidence Retrieval Guided Attention for Enhanced Document-level Relation Extraction

TL;DR

GEGA is a novel model that enhances document-level relation extraction by integrating graph neural networks and evidence retrieval guided attention, significantly improving performance on benchmark datasets.

Contribution

The paper introduces GEGA, a new approach combining graph neural networks and evidence-guided attention for better relation extraction from long documents.

Findings

Achieved state-of-the-art results on DocRED, Re-DocRED, and Revisit-DocRED datasets.

Effectively guides attention to relevant evidence sentences, improving extraction accuracy.

Enhances multi-scale representation aggregation for better understanding of complex relations.

Abstract

Document-level relation extraction (DocRE) aims to extract relations between entities from unstructured document text. Compared to sentence-level relation extraction, it requires more complex semantic understanding from a broader text context. Currently, some studies are utilizing logical rules within evidence sentences to enhance the performance of DocRE. However, in the data without provided evidence sentences, researchers often obtain a list of evidence sentences for the entire document through evidence retrieval (ER). Therefore, DocRE suffers from two challenges: firstly, the relevance between evidence and entity pairs is weak; secondly, there is insufficient extraction of complex cross-relations between long-distance multi-entities. To overcome these challenges, we propose GEGA, a novel model for DocRE. The model leverages graph neural networks to construct multiple weight matrices, guiding attention allocation to evidence sentences. It also employs multi-scale representation aggregation to enhance ER. Subsequently, we integrate the most efficient evidence information to implement both fully supervised and weakly supervised training processes for the model. We evaluate the GEGA model on three widely used benchmark datasets: DocRED, Re-DocRED, and Revisit-DocRED. The experimental results indicate that our model has achieved comprehensive improvements compared to the existing SOTA model.