Improving Cross-Domain Chinese Word Segmentation with Word Embeddings

Yuxiao Ye, Weikang Li, Yue Zhang, Likun Qiu, Jian Sun


Abstract
Cross-domain Chinese Word Segmentation (CWS) remains a challenge despite recent progress in neural-based CWS. The limited amount of annotated data in the target domain has been the key obstacle to a satisfactory performance. In this paper, we propose a semi-supervised word-based approach to improving cross-domain CWS given a baseline segmenter. Particularly, our model only deploys word embeddings trained on raw text in the target domain, discarding complex hand-crafted features and domain-specific dictionaries. Innovative subsampling and negative sampling methods are proposed to derive word embeddings optimized for CWS. We conduct experiments on five datasets in special domains, covering domains in novels, medicine, and patent. Results show that our model can obviously improve cross-domain CWS, especially in the segmentation of domain-specific noun entities. The word F-measure increases by over 3.0% on four datasets, outperforming state-of-the-art semi-supervised and unsupervised cross-domain CWS approaches with a large margin. We make our data and code available on Github.
Anthology ID:
N19-1279
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2726–2735
Language:
URL:
https://www.aclweb.org/anthology/N19-1279
DOI:
10.18653/v1/N19-1279
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N19-1279.pdf