Adversarial Training for Relation Extraction

Yi Wu, David Bamman, Stuart Russell


Abstract
Adversarial training is a mean of regularizing classification algorithms by generating adversarial noise to the training data. We apply adversarial training in relation extraction within the multi-instance multi-label learning framework. We evaluate various neural network architectures on two different datasets. Experimental results demonstrate that adversarial training is generally effective for both CNN and RNN models and significantly improves the precision of predicted relations.
Anthology ID:
D17-1187
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:
1778–1783
Language:
URL:
https://www.aclweb.org/anthology/D17-1187
DOI:
10.18653/v1/D17-1187
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1187.pdf