Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoning

Benchmark Model Rank Results
relation-extraction-on-cdrCGM2IR-SciBERTbase–F1: 73.8
relation-extraction-on-docredCGM2IR-BERTbase–F1: 62.06Ign F1: 60.24
relation-extraction-on-docredCGM2IR-RoBERTalarge–F1: 63.89Ign F1: 61.96
relation-extraction-on-gdaCGM2IR-SciBERTbase–F1: 84.7