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

by   Qingyu Tan, et al.

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


page 1

page 2

page 3

page 4


A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents

Distantly supervised datasets for relation extraction mostly focus on se...

Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data

Relation extraction (RE) aims to extract relations from sentences and do...

PP-StructureV2: A Stronger Document Analysis System

A large amount of document data exists in unstructured form such as raw ...

Deep Class Incremental Learning from Decentralized Data

In this paper, we focus on a new and challenging decentralized machine l...

Entity Concept-enhanced Few-shot Relation Extraction

Few-shot relation extraction (FSRE) is of great importance in long-tail ...

Learning Logic Rules for Document-level Relation Extraction

Document-level relation extraction aims to identify relations between en...

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

Document-level relation extraction (RE) poses new challenges compared to...

Please sign up or login with your details

Forgot password? Click here to reset