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

Autor:	Tan, Qingyu, He, Ruidan, Bing, Lidong, Ng, Hwee Tou
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: To appear in the Findings of ACL 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.10900 Zobrazit plný text záznamu View this record from Arxiv