An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning

Open paper
Benchmark Model Rank Results
joint-entity-and-relation-extraction-on-docredJEREX#3Relation F1: 40.38
relation-extraction-on-docredJEREX-BERT-base#22F1: 60.40Ign F1: 58.44
relation-extraction-on-redocredJEREX#8F1: 72.57Ign F1: 71.45

Rank counts only results with a code link.