Domain Adaptation for Relation Extraction with Domain Adversarial Neural Network

Lisheng Fu, Thien Huu Nguyen, Bonan Min, Ralph Grishman


Abstract
Relations are expressed in many domains such as newswire, weblogs and phone conversations. Trained on a source domain, a relation extractor’s performance degrades when applied to target domains other than the source. A common yet labor-intensive method for domain adaptation is to construct a target-domain-specific labeled dataset for adapting the extractor. In response, we present an unsupervised domain adaptation method which only requires labels from the source domain. Our method is a joint model consisting of a CNN-based relation classifier and a domain-adversarial classifier. The two components are optimized jointly to learn a domain-independent representation for prediction on the target domain. Our model outperforms the state-of-the-art on all three test domains of ACE 2005.
Anthology ID:
I17-2072
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
425–429
Language:
URL:
https://aclanthology.org/I17-2072
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/I17-2072.pdf