Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs

24 May 2021  ·  Tianming Liang, Yang Liu, Xiaoyan Liu, Hao Zhang, Gaurav Sharma, Maozu Guo ·

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. The pre-processed datasets and source code are publicly available at https://github.com/tmliang/CGRE.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relationship Extraction (Distant Supervised) New York Times Corpus CGRE P@10% 84.5 # 3
P@30% 71.5 # 3
AUC 0.52 # 1