CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
周玉; 宗成庆; 徐波
Source Publication中文信息学报
Other AbstractIn this paper we propose anew algorithm called muhi-layer fiherirIg to exiract the bilingual alignment chunks alltomatically from Chinese-English parallel texts.Various layers are sed to extract bilingual chunks according to different features possessed by diffemm chunks in the bilingual corpus.Our chunking and alignment algorithm does not rely On the informarion from tagging,parsing or syntax analyzing as most conventional algorithms do.The preliminary experimental results express that our algorithm achieves a good performance in chunking and alignment.The F-measure of chunking is 0.7 and the F-measure of alignment is 0.8.Moreover,the translatiolls generated by this algorithm are much better than the results
generated by the baseline word alignment algorithm;it almost improves of 10%.
Keyword人工智能 机器翻译 多层过滤 双语语块识别与对齐
Document Type期刊论文
Recommended Citation
GB/T 7714
周玉,宗成庆,徐波. 基于多层过滤的统计机器翻译[J]. 中文信息学报,2005,19(3):54-60.
APA 周玉,宗成庆,&徐波.(2005).基于多层过滤的统计机器翻译.中文信息学报,19(3),54-60.
MLA 周玉,et al."基于多层过滤的统计机器翻译".中文信息学报 19.3(2005):54-60.
Files in This Item: Download All
File Name/Size DocType Version Access License
42-基于多层过滤的统计机器翻译.pdf(367KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[周玉]'s Articles
[宗成庆]'s Articles
[徐波]'s Articles
Baidu academic
Similar articles in Baidu academic
[周玉]'s Articles
[宗成庆]'s Articles
[徐波]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[周玉]'s Articles
[宗成庆]'s Articles
[徐波]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 42-基于多层过滤的统计机器翻译.pdf
Format: Adobe PDF
All comments (0)
No comment.

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