Document-Level Relation Extraction Based on Heterogeneous Graph Reasoning
Dong Li, Miao Li, Zhi-Lei Lei, Baoyan Song, Xiaohuan Shan · 2024
The goal of document-level relation extraction is to extract semantic information from multiple sentences within a document and identify the relations between entities across sentences. However, effectively representing the document's content and reasoning about cross-sentence entities presents a formidable challenge. In this paper, we propose an efficient Document-Level Relation Extraction Model based on Heterogeneous Graph Reasoning (HGR-DREM), which enables relation extraction more accurate. Specifically, we first construct a document-level heterogeneous graph to comprehensively capture the semantic relations between entities. Then, we design a meta-path attention-based reasoning mechanism to enhance the mutual influence among graph nodes. Furthermore, we utilize an extended adjacency matrix to represent the heterogeneous graph and leverage graph convolutional neural networks (GCNs) to extract high-dimensional features. The experiments on a real-world dataset demonstrate the effectiveness of our proposed model. All codes have been released at https://github.com/NuyoaH-code/HGR-DREM.