XJIPC OpenIR  > 多语种信息技术研究室
陈科海; 周喜; 杨雅婷; 米成刚
Source Publication计算机应用研究


Other Abstract

Aimed at the serious problem of phenomenon that there are so many Out-Of-Vocabulary words and translation disorder in Uyghur-Chinese machine translation, and combined the features of Uyghur and The maximum entropy classification algorithm, the paper presents an Max Entropy Reordering model in Uyghur-Chinese machine translation based on tackiness fuzzy rules. The model is based on Max Entropy classification algorithm,and create the Constraints of tackiness fuzzy rules for Uyghur in the word level , then extracts better effective reordering rules from training corpus to guide the translation decoding procedure. The experiments show that compared with the current reordering methods, such as MSD(mono、swap、discontinuous) and so on, this reordering method is better retained the tackiness feature of Uyghur , and the quality of the translation is also improved.

Keyword维汉机器翻译 形态学 粘着性 模糊规则 最大熵 调序模型
Indexed ByCSCD
Citation statistics
Document Type期刊论文
Recommended Citation
GB/T 7714
陈科海,周喜,杨雅婷,等. 基于粘着性模糊规则的维汉机器翻译最大熵调序研究[J]. 计算机应用研究,2013,30(9):2587-2590+2605.
APA 陈科海,周喜,杨雅婷,&米成刚.(2013).基于粘着性模糊规则的维汉机器翻译最大熵调序研究.计算机应用研究,30(9),2587-2590+2605.
MLA 陈科海,et al."基于粘着性模糊规则的维汉机器翻译最大熵调序研究".计算机应用研究 30.9(2013):2587-2590+2605.
Files in This Item:
File Name/Size DocType Version Access License
基于粘着性模糊规则的维汉机器翻译最大熵调(457KB)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
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[陈科海]'s Articles
[周喜]'s Articles
[杨雅婷]'s Articles
Baidu academic
Similar articles in Baidu academic
[陈科海]'s Articles
[周喜]'s Articles
[杨雅婷]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[陈科海]'s Articles
[周喜]'s Articles
[杨雅婷]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于粘着性模糊规则的维汉机器翻译最大熵调序研究.pdf
Format: Adobe PDF
All comments (0)
No comment.

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