CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation
Wang, Kun1; Zong, Chengqing1; Su, Keh-Yih2
Source PublicationACM Transactions on Asian Language Information Processing (TALIP)
2012-06
Volume11Issue:2Pages:7:1-7:41
Abstract
Among statistical approaches to Chinese word segmentation, the word-based n-gram (generative) model and the character-based tagging (discriminative) model are two dominant approaches in the literature. The former gives excellent performance for the in-vocabulary (IV) words; however, it handles out-of-vocabulary(OOV) words poorly. On the other hand, though the latter is more robust for OOV words, it fails to deliver satisfactory performance for IV words. These two approaches behave differently due to the unit they use(word vs. character) and the model form they adopt (generative vs. discriminative). In general, characterbased approaches are more robust than word-based ones, as the vocabulary of characters is a closed set;and discriminative models are more robust than generative ones, since they can flexibly include all kinds of available information, such as future context. This article first proposes a character-based n-gram model to enhance the robustness of the generative approach. Then the proposed generative model is further integrated with the character-based discriminative model to take advantage of both approaches. Our experiments show that this integrated approach outperforms all the existing approaches reported in the literature. Afterwards, a complete and detailed
error analysis is conducted. Since a significant portion of the critical errors is related to numerical/foreign strings, character-type information is then incorporated into the model to further improve its performance. Last, the proposed integrated approach is tested on cross-domain corpora, and
KeywordChinese Word Segmentation
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12364
Collection模式识别国家重点实验室_自然语言处理
Corresponding AuthorWang, Kun
Affiliation1.中国科学院自动化研究所
2.Behavior Design Corporation
Recommended Citation
GB/T 7714
Wang, Kun,Zong, Chengqing,Su, Keh-Yih. Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation[J]. ACM Transactions on Asian Language Information Processing (TALIP),2012,11(2):7:1-7:41.
APA Wang, Kun,Zong, Chengqing,&Su, Keh-Yih.(2012).Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation.ACM Transactions on Asian Language Information Processing (TALIP),11(2),7:1-7:41.
MLA Wang, Kun,et al."Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation".ACM Transactions on Asian Language Information Processing (TALIP) 11.2(2012):7:1-7:41.
Files in This Item: Download All
File Name/Size DocType Version Access License
2012.06 ACM TALIP K.(790KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Kun]'s Articles
[Zong, Chengqing]'s Articles
[Su, Keh-Yih]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Kun]'s Articles
[Zong, Chengqing]'s Articles
[Su, Keh-Yih]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Kun]'s Articles
[Zong, Chengqing]'s Articles
[Su, Keh-Yih]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2012.06 ACM TALIP K.Wang.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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