XJIPC OpenIR  > 多语种信息技术研究室
Co-occurrence degree based word alignment in statistical machine translation
Mi, Chenggang1; Yang, Yating1; Wang, Lei1; Li, Xiao1
2014
Source PublicationOpen Automation and Control Systems Journal
Volume6Issue:1Pages:561-565
AbstractTo alleviate the data sparseness problem during word alignment, we propose a word alignment method based on word co-occurrence degree. In this paper, we propose a new method to get the statistical information from word cooccurrence. We combine the co-occurrence counts and the fuzzy co-occurrence weights as word co-occurrence degree. Fuzzy co-occurrence weights can be obtained by searching for fuzzy co-occurrence word pairs and computing differences of length between current word and other words in fuzzy co-occurrence word pairs. Experiments show that the quality of word alignment and the translation performance both improved.
KeywordCo -occurrence Degree Statistical Machine Translatio Word Alignment
Indexed ByEI
Document Type期刊论文
Identifierhttp://ir.xjipc.cas.cn/handle/365002/4913
Collection多语种信息技术研究室
Affiliation1.Xinjiang Technical Institute of Physics and Chemistry of Chinese Academy of Sciences, Urumqi, China
2.University of Chinese Academy of Sciences, Beijing, China
Recommended Citation
GB/T 7714
Mi, Chenggang,Yang, Yating,Wang, Lei,et al. Co-occurrence degree based word alignment in statistical machine translation[J]. Open Automation and Control Systems Journal,2014,6(1):561-565.
APA Mi, Chenggang,Yang, Yating,Wang, Lei,&Li, Xiao.(2014).Co-occurrence degree based word alignment in statistical machine translation.Open Automation and Control Systems Journal,6(1),561-565.
MLA Mi, Chenggang,et al."Co-occurrence degree based word alignment in statistical machine translation".Open Automation and Control Systems Journal 6.1(2014):561-565.
Files in This Item:
File Name/Size DocType Version Access License
Co-occurrence degree(2130KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Mi, Chenggang]'s Articles
[Yang, Yating]'s Articles
[Wang, Lei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Mi, Chenggang]'s Articles
[Yang, Yating]'s Articles
[Wang, Lei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Mi, Chenggang]'s Articles
[Yang, Yating]'s Articles
[Wang, Lei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Co-occurrence degree based word alignment in statistical machine translation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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