Double Graph Based Reasoning for Document-level Relation Extraction

EMNLP 2020  ·  Shuang Zeng, Runxin Xu, Baobao Chang, Lei LI ·

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN) featuring double graphs. GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document. It also constructs an entity-level graph (EG), based on which we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at .

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction DocRED GAIN-BERT-large F1 62.76 # 12
Ign F1 60.31 # 15
Relation Extraction DocRED GAIN-BERT F1 61.24 # 27
Ign F1 59.00 # 28
Relation Extraction DocRED GAIN-GloVe F1 55.08 # 53
Ign F1 52.66 # 53


No methods listed for this paper. Add relevant methods here