XJIPC OpenIR  > 多语种信息技术研究室
汉维统计机器翻译中的形态学处理
Alternative Titlemorphology processing in chinese-uyghur statistical machine translation
董兴华; 陈丽娟; 周喜; 周俊林; 吐尔洪·吾司曼
2011
Source Publication计算机工程
ISSN1000-3428
Volume37Issue:12Pages:150-152
Abstract

针对汉语和维吾尔语语序差别(前者是主-谓-宾结构,后者是主-宾-谓结构)及形态差别较大的问题,通过编写调序规则将汉语调整为主-宾-谓结构,将维吾尔语单词切分为词干、词缀等更小的词素单元来训练统计模型,同时测试词素的切分粒度对翻译性能的影响。实验结果表明,对汉语句法结构的调整及以词干、词缀等更小的词素形式参与训练可以有效提高翻译质量。

Other Abstract

For the large differences of syntactic structure between Chinese and Uyghur,it composes rules to reorder the structure of Chinese sentences to that of Uyghur.For the large morphological differences between Chinese and Uyghur,it splits Uyghur words into stems and affixes,that is,morphemes,to train the statistical model.Meanwhile,it tests the effects of splitting granularities on translation performance.Experimental results show Chinese sentence reordering and splitting Uyghur words into morphemes can effectively improve the performance of translation system.

Keyword汉维 统计机器翻译 词素 调序
Indexed ByCSCD
CSCD IDCSCD:4225918
Citation statistics
Cited Times:2[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.xjipc.cas.cn/handle/365002/1561
Collection多语种信息技术研究室
Affiliation中国科学院新疆理化技术研究所;中国科学院新疆分院
Recommended Citation
GB/T 7714
董兴华,陈丽娟,周喜,等. 汉维统计机器翻译中的形态学处理[J]. 计算机工程,2011,37(12):150-152.
APA 董兴华,陈丽娟,周喜,周俊林,&吐尔洪·吾司曼.(2011).汉维统计机器翻译中的形态学处理.计算机工程,37(12),150-152.
MLA 董兴华,et al."汉维统计机器翻译中的形态学处理".计算机工程 37.12(2011):150-152.
Files in This Item:
File Name/Size DocType Version Access License
汉维统计机器翻译中的形态学处理.pdf(1031KB)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
[董兴华]'s Articles
[陈丽娟]'s Articles
[周喜]'s Articles
Baidu academic
Similar articles in Baidu academic
[董兴华]'s Articles
[陈丽娟]'s Articles
[周喜]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[董兴华]'s Articles
[陈丽娟]'s Articles
[周喜]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 汉维统计机器翻译中的形态学处理.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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