Revisiting the Negative Data of Distantly Supervised Relation Extraction
Distantly supervised relation extraction treats unlabeled data as negative, but analysis reveals hidden positives and noisy labels cause false negatives. Cleaning negative data improves model training and extraction performance significantly.
Published 202124 citationsPaper ↗
70%
OverallHighly rated
?
OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.
Readers
–
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel5/20reviewers recommend it
lenient 1/5
medium 3/10
strict 1/5
AI panel?Vote to see what the 20 AI reviewers said
The paper earns praise for a rigorous, teachable negative-sampling framework that corrects distant supervision at the data level, but its lasting impact is undermined by missing open-source filtering code, uncertain standard-bag compatibility, and zero follow-up architecture…
Abstract
Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang, Wenhao Huang, Yanghua Xiao. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.