Document-level Relation Extraction as Semantic Segmentation

Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples. Experimental results show that our approach can obtain state-of-the-art performance on three benchmark datasets DocRED, CDR, and GDA.

Authors

• Ningyu Zhang Zhejiang University Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph
• Xiang Chen Zhejiang University
• Xin Xie
• Shumin Deng NUS-NCS Joint Lab, National University of Singapore
• Chuanqi Tan
• Mosha Chen
• Fei Huang Tongyi Lab
• Luo Si DAMO Academy, Alibaba Group
• Huajun Chen College of Computer Science and Technology, Zhejiang University ZJU-Ant Group Joint Lab of Knowledge Graph Zhejiang Key Laboratory of Big Data Intelligent Computing

Keywords

• Natural Language Processing: Information Extraction
• Natural Language Processing: Knowledge Extraction