Document-level Relation Extraction as Semantic Segmentation

7 Jun 2021  ·  Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng, Chuanqi Tan, Mosha Chen, Fei Huang, Luo Si, Huajun Chen ·

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.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction CDR DocuNet-SciBERTbase F1 76.3 # 4
Relation Extraction DocRED DocuNet-RoBERTa-large F1 64.55 # 6
Ign F1 62.4 # 6
Relation Extraction GDA DocuNet-SciBERTbase F1 85.3 # 4
Relation Extraction ReDocRED DocuNET F1 77.87 # 4
Ign F1 77.26 # 4


No methods listed for this paper. Add relevant methods here