Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation

Ning Ding, Dingkun Long, Guangwei Xu, Muhua Zhu, Pengjun Xie, Xiaobin Wang, Haitao Zheng


Abstract
Fully supervised neural approaches have achieved significant progress in the task of Chinese word segmentation (CWS). Nevertheless, the performance of supervised models always drops gravely if the domain shifts due to the distribution gap across domains and the out of vocabulary (OOV) problem. In order to simultaneously alleviate the issues, this paper intuitively couples distant annotation and adversarial training for cross-domain CWS. 1) We rethink the essence of “Chinese words” and design an automatic distant annotation mechanism, which does not need any supervision or pre-defined dictionaries on the target domain. The method could effectively explore domain-specific words and distantly annotate the raw texts for the target domain. 2) We further develop a sentence-level adversarial training procedure to perform noise reduction and maximum utilization of the source domain information. Experiments on multiple real-world datasets across various domains show the superiority and robustness of our model, significantly outperforming previous state-of-the-arts cross-domain CWS methods.
Anthology ID:
2020.acl-main.595
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6662–6671
Language:
URL:
https://aclanthology.org/2020.acl-main.595
DOI:
10.18653/v1/2020.acl-main.595
Bibkey:
Cite (ACL):
Ning Ding, Dingkun Long, Guangwei Xu, Muhua Zhu, Pengjun Xie, Xiaobin Wang, and Haitao Zheng. 2020. Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6662–6671, Online. Association for Computational Linguistics.
Cite (Informal):
Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation (Ding et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2020.acl-main.595.pdf
Video:
 http://slideslive.com/38928996
Code
 Alibaba-NLP/DAAT-CWS