CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Integrating Surface and Abstract Features for Robust Cross-Domain Chinese Word Segmentation
Li XQ(李小青); Wang Kun; Zong Chengqing; Su Keh-Yih; Li, Xiaoqing
2012
Conference NameInternational Conference on Computational Linguistics
Source PublicationProceedings of 24th International Conference on Computational Linguistics
Conference Date8-15, December
Conference PlaceBombay, India
Abstract
Current character-based approaches are not robust for cross domain Chinese word segmentation. In this paper, we alleviate this problem by deriving a novel enhanced character-based generative model with a new abstract aggregate candidate-feature, which indicates if the given candidate prefers the corresponding position-tag of the longest dictionary matching word. Since the distribution of the proposed feature is invariant across domains, our model thus possesses better generalization ability. Open tests on CIPS-SIGHAN-2010 show that the enhanced generative model achieves robust cross-domain performance for various OOV coverage rates and obtains the best performance on three out of four domains. The enhanced generative model is then further integrated with a discriminative model which also utilizes dictionary information. This integrated model is shown to be either superior or comparable to all other models reported in the literature
on every domain of this task.
KeywordWord Segmentation Dictionary
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13017
Collection模式识别国家重点实验室_自然语言处理
Corresponding AuthorLi, Xiaoqing
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Li XQ,Wang Kun,Zong Chengqing,et al. Integrating Surface and Abstract Features for Robust Cross-Domain Chinese Word Segmentation[C],2012.
Files in This Item: Download All
File Name/Size DocType Version Access License
Integrating Surface (394KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li XQ(李小青)]'s Articles
[Wang Kun]'s Articles
[Zong Chengqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li XQ(李小青)]'s Articles
[Wang Kun]'s Articles
[Zong Chengqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li XQ(李小青)]'s Articles
[Wang Kun]'s Articles
[Zong Chengqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Integrating Surface and Abstract Features for Robust Cross-Domain Chinese Word Segmentation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.