Abstract
This paper presents a novel hybrid generative/discriminative model of word segmentation based on nonparametric Bayesian methods. Unlike ordinary discriminative word segmentation which relies only on labeled data, our semi-supervised model also leverages a huge amounts of unlabeled text to automatically learn new “words”, and further constrains them by using a labeled data to segment non-standard texts such as those found in social networking services. Specifically, our hybrid model combines a discriminative classifier (CRF; Lafferty et al. (2001) and unsupervised word segmentation (NPYLM; Mochihashi et al. (2009)), with a transparent exchange of information between these two model structures within the semi-supervised framework (JESS-CM; Suzuki and Isozaki (2008)). We confirmed that it can appropriately segment non-standard texts like those in Twitter and Weibo and has nearly state-of-the-art accuracy on standard datasets in Japanese, Chinese, and Thai.- Anthology ID:
- Q17-1013
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 5
- Month:
- Year:
- 2017
- Address:
- Cambridge, MA
- Editors:
- Lillian Lee, Mark Johnson, Kristina Toutanova
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 179–189
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/Q17-1013/
- DOI:
- 10.1162/tacl_a_00054
- Cite (ACL):
- Ryo Fujii, Ryo Domoto, and Daichi Mochihashi. 2017. Nonparametric Bayesian Semi-supervised Word Segmentation. Transactions of the Association for Computational Linguistics, 5:179–189.
- Cite (Informal):
- Nonparametric Bayesian Semi-supervised Word Segmentation (Fujii et al., TACL 2017)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/Q17-1013.pdf