Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation

Document-level Relation Extraction (DocRE) is a more challenging task compared to its sentence-level counterpart. It aims to extract relations from multiple sentences at once. In this paper, we propose a semi-supervised framework for DocRE with three novel components. Firstly, we use an axial attention module for learning the interdependency among entity-pairs, which improves the performance on two-hop relations. Secondly, we propose an adaptive focal loss to tackle the class imbalance problem of DocRE. Lastly, we use knowledge distillation to overcome the differences between human annotated data and distantly supervised data. We conducted experiments on two DocRE datasets. Our model consistently outperforms strong baselines and its performance exceeds the previous SOTA by 1.36 F1 and 1.46 Ign_F1 score on the DocRED leaderboard. Our code and data will be released at https://github.com/tonytan48/KD-DocRE.

PDF Abstract Findings (ACL) 2022 PDF Findings (ACL) 2022 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction DocRED KD-Rb-l F1 67.28 # 2
Ign F1 65.24 # 2
Relation Extraction ReDocRED KD-DocRE F1 78.28 # 4
Ign F1 77.60 # 4

Methods