| 基于句子比较的英汉翻译模板自动提取算法 |
| |
| 引用本文： | 廖剑,李玉鑑.基于句子比较的英汉翻译模板自动提取算法[J].计算机工程与应用,2006,42(25):176-179. |
| |
| 作者姓名： | 廖剑 李玉鑑 |
| |
| 作者单位： | 北京工业大学计算机学院,多媒体与智能软件北京市重点实验室,北京,100022 |
| |
| 基金项目： | 北京市自然科学基金;北京市教委科技发展计划 |
| |
| 摘 要： | 模板的自动抽取算法对机器翻译的研究具有重要意义。从面向英汉翻译的角度出发,论文对基于句子比较的翻译模板抽取(ATTEBSC)算法及其改进开展了比较研究,结果发现传统ATTEBSC算法在处理大规模语料库时运行效率较低,而且产生的无用模板比例较高,其中一个重要原因是没有事先对双语对齐语料库进行分类处理。通过相似性分析对句子进行聚类处理后再运行ATTEBSC算法,则发现该算法的运行效率和有用模板的比例都获得了较大的提高。
|
| 关 键 词： | 句子比较 模板 分类 机器翻译 |
| 文章编号： | 1002-8331-（2006）25-0176-04 |
| 收稿时间： | 2005-09 |
| 修稿时间： | 2005-09 |
Automatic Extraction Algorithm of English-Chinese Translation Templates Based on Sentences Comparison |
| |
| LIAO Jian,LI Yu-jian.Automatic Extraction Algorithm of English-Chinese Translation Templates Based on Sentences Comparison[J].Computer Engineering and Applications,2006,42(25):176-179. |
| |
| Authors: | LIAO Jian LI Yu-jian |
| |
| Affiliation: | Beijing Municipal Key Lab of Multimedia and Intelligent Software Technology,College of Computer Science and Technology,Beijing University of Technology,Beijing 100022 |
| |
| Abstract: | Automatic extraction algorithm is very important to machine translation research.From the viewpoint of English-Chinese translation,this paper gives a study of the ATTEBSC algorithm and its improvement,where ATTEBSC refers to "Automatic Translation Templates Extraction Based on Sentences Comparison".It is shown that the traditional ATTEBSC algorithm is inefficient with a high ratio of useless templates,one important reason is lack of classification for bilingual corpus.If the ATTEBSC algorithm runs after clustering on bilingual corpus,it performs with a good improvement in efficiency and usefulness of templates. |
| |
| Keywords: | sentence comparison template classification machine translation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
