.png){kind=icon}
返回
Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2022.3177226.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Relation extraction
distant supervision
multi-instance learning
label noise
long tail
期刊
IF:
10.4
论文数:
6.9K
被引数:
3.2W
机构
引用论文
The Source, Spatial Distribution and Risk Assessment of Heavy Metals in Soil from the Pearl River Delta Based on the National Multi-Purpose Regional Geochemical Survey.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏Population screening for the common G985 mutation causing medium-chain acyl-CoA dehydrogenase deficiency with Eu-labeled oligonucleotides and the DELFIA system用Eu标记的寡核苷酸和DELFIA系统筛选引起中链酰基辅酶a脱氢酶缺乏症的常见G985突变的人群
OAAI
OAAI分享收藏
查看更多内容