Adversarial training for multi-context joint entity and relation extraction

Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder


Abstract
Adversarial training (AT) is a regularization method that can be used to improve the robustness of neural network methods by adding small perturbations in the training data. We show how to use AT for the tasks of entity recognition and relation extraction. In particular, we demonstrate that applying AT to a general purpose baseline model for jointly extracting entities and relations, allows improving the state-of-the-art effectiveness on several datasets in different contexts (i.e., news, biomedical, and real estate data) and for different languages (English and Dutch).
Anthology ID:
D18-1307
Original:
D18-1307v1
Version 2:
D18-1307v2
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2830–2836
Language:
URL:
https://www.aclweb.org/anthology/D18-1307
DOI:
10.18653/v1/D18-1307
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-1307.pdf
Video:
 https://vimeo.com/306055549