Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation
This work addresses the challenging problem of extracting relations from multiple sentences for natural language processing applications, representing an incremental advance with specific performance gains.
The paper tackles document-level relation extraction by proposing a semi-supervised framework with axial attention, adaptive focal loss, and knowledge distillation, achieving a 1.36 F1 and 1.46 Ign_F1 improvement over previous state-of-the-art on the DocRED leaderboard.
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.