Domain Adaptation for Disease Phrase Matching with Adversarial Networks

Miaofeng Liu, Jialong Han, Haisong Zhang, Yan Song


Abstract
With the development of medical information management, numerous medical data are being classified, indexed, and searched in various systems. Disease phrase matching, i.e., deciding whether two given disease phrases interpret each other, is a basic but crucial preprocessing step for the above tasks. Being capable of relieving the scarceness of annotations, domain adaptation is generally considered useful in medical systems. However, efforts on applying it to phrase matching remain limited. This paper presents a domain-adaptive matching network for disease phrases. Our network achieves domain adaptation by adversarial training, i.e., preferring features indicating whether the two phrases match, rather than which domain they come from. Experiments suggest that our model has the best performance among the very few non-adaptive or adaptive methods that can benefit from out-of-domain annotations.
Anthology ID:
W18-2315
Volume:
Proceedings of the BioNLP 2018 workshop
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Dina Demner-Fushman, Kevin Bretonnel Cohen, Sophia Ananiadou, Junichi Tsujii
Venue:
BioNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
137–141
Language:
URL:
https://aclanthology.org/W18-2315
DOI:
10.18653/v1/W18-2315
Bibkey:
Cite (ACL):
Miaofeng Liu, Jialong Han, Haisong Zhang, and Yan Song. 2018. Domain Adaptation for Disease Phrase Matching with Adversarial Networks. In Proceedings of the BioNLP 2018 workshop, pages 137–141, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Domain Adaptation for Disease Phrase Matching with Adversarial Networks (Liu et al., BioNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-2315.pdf