NC-DRE: Leveraging Non-entity Clue Information for Document-level Relation Extraction

TL;DR

This paper introduces NC-DRE, a novel graph-based model for document-level relation extraction that leverages non-entity clue words through a decoder-to-encoder attention mechanism, enhancing reasoning across multiple sentences.

Contribution

The paper proposes a new model that incorporates non-entity clue words into document-level RE by modifying the encoder-decoder framework with a decoder-to-encoder attention mechanism.

Findings

Improved relation extraction accuracy on benchmark datasets.

Effective utilization of non-entity clues enhances inter-sentence reasoning.

Demonstrates the advantage of decoder-to-encoder attention in GNN-based RE models.

Abstract

Document-level relation extraction (RE), which requires reasoning on multiple entities in different sentences to identify complex inter-sentence relations, is more challenging than sentence-level RE. To extract the complex inter-sentence relations, previous studies usually employ graph neural networks (GNN) to perform inference upon heterogeneous document-graphs. Despite their great successes, these graph-based methods, which normally only consider the words within the mentions in the process of building graphs and reasoning, tend to ignore the non-entity clue words that are not in the mentions but provide important clue information for relation reasoning. To alleviate this problem, we treat graph-based document-level RE models as an encoder-decoder framework, which typically uses a pre-trained language model as the encoder and a GNN model as the decoder, and propose a novel graph-based model NC-DRE that introduces decoder-to-encoder attention mechanism to leverage Non-entity Clue information for Document-level Relation Extraction.