A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction

Tianyu Liu, Kexiang Wang, Baobao Chang, Zhifang Sui


Abstract
Distant-supervised relation extraction inevitably suffers from wrong labeling problems because it heuristically labels relational facts with knowledge bases. Previous sentence level denoise models don’t achieve satisfying performances because they use hard labels which are determined by distant supervision and immutable during training. To this end, we introduce an entity-pair level denoise method which exploits semantic information from correctly labeled entity pairs to correct wrong labels dynamically during training. We propose a joint score function which combines the relational scores based on the entity-pair representation and the confidence of the hard label to obtain a new label, namely a soft label, for certain entity pair. During training, soft labels instead of hard labels serve as gold labels. Experiments on the benchmark dataset show that our method dramatically reduces noisy instances and outperforms other state-of-the-art systems.
Anthology ID:
D17-1189
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1790–1795
URL:
https://www.aclweb.org/anthology/D17-1189
DOI:
10.18653/v1/D17-1189
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D17-1189.pdf