Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs
- 23 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (7) , 6852-6865
Abstract
Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In this paper, we introduce a constraint graph to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Extensive experimental results indicate that CGRE achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61871020, 61976071, 62031003, 62071154)
- National Key Research and Development Program of China (2016YFC0901902)
- High Level Innovation Team Construction Project of Beijing Municipal Universities (IDHT20190506)
This publication has 49 references indexed in Scilit:
- Answering Natural Language Questions by Subgraph Matching over Knowledge GraphsIEEE Transactions on Knowledge and Data Engineering, 2017
- Exploring Long Tail Data in Distantly Supervised Relation Extraction2016
- Generating Query Facets Using Knowledge BasesIEEE Transactions on Knowledge and Data Engineering, 2016
- Neural Relation Extraction with Selective Attention over Instances2016
- Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks2015
- Large-Scale Learning of Relation-Extraction Rules with Distant Supervision from the Web2012
- Modeling Relations and Their Mentions without Labeled Text2010
- SemEval-2010 task 82009
- Distant supervision for relation extraction without labeled data2009
- Web People Search via Connection AnalysisIEEE Transactions on Knowledge and Data Engineering, 2008