| 限定领域的汉语-维吾尔语句子级对齐研究 |
| |
| 引用本文： | 张亚军,贺琛琛,香丽芸.限定领域的汉语-维吾尔语句子级对齐研究[J].软件,2014(3):62-64. |
| |
| 作者姓名： | 张亚军 贺琛琛 香丽芸 |
| |
| 作者单位： | [1]昌吉学院计算机工程系,新疆昌吉831100 [2]昌吉学院人事处,新疆昌吉831100 |
| |
| 基金项目： | 本课题基金资助国家自然科学基金（National Natural Science Foundation of China项目编号60963018）;新疆维吾尔自治区高校科研计划青年教师科研基金项目（University research programs of young teachers in the Xinjiang Uygur Autonomous Region Fund项目编号XJEDU2011S42）;昌吉学院项目（Changji university researchfund项目编号：2012YJQT03,12JYYB004） |
| |
| 摘 要： | 针对政府文献的汉语维吾尔语语料库特点，充分利用汉语和维吾尔语的句子特性，提出一种汉维句子级别的对齐方法。该方法重点分析政府领域的汉语和维吾尔语的句型，分别对汉语和维吾尔语的语料进行边界识别，避免了复杂句型对汉语-维吾尔语句子对齐的影响，使得该方法取得句子对齐达到97%与99%之间的正确率。对齐的汉语-维吾尔语句子对可以充实语料库的规模，为汉语-维吾尔语短语对齐以及汉维机器翻译提供翻译语料。
|
| 关 键 词： | 平行语料库 句子对齐 机器翻译 汉语-维吾尔语 句子边界识别 |
Limited the Field of Chinese-Uighur Statement Sub-level Alignment |
| |
| ZHANG Ya-jun,HE Chen-chen,XIANG Li-yun.Limited the Field of Chinese-Uighur Statement Sub-level Alignment[J].Software,2014(3):62-64. |
| |
| Authors: | ZHANG Ya-jun HE Chen-chen XIANG Li-yun |
| |
| Affiliation: | (Changji College, Changji,Xinjiang 831100,China) |
| |
| Abstract: | Chinese Uighur Corpus characteristics for government documents, and take full advantage of the features of Chinese and Uighur’s sentence, and put forward Chinese-Uighur sentence level alignment. The method analyzes government areas of Chinese and Uighur’s sentence boundary identification of the corpus of Chinese and Uighur, to avoid the impact of complex sentences in Chinese and Uygur sentence aligned, which makes the method to obtain the sentence alignment up to 97%and 99%correct rate. Alignment of the Chinese-Uighur statement that the child can enrich the corpus of the scale, Chinese-Uighur phrase alignment and machine translation in Chinese and Uygur translation corpus. |
| |
| Keywords: | parallel corpus sentence alignment machine translation Chinese-Uighur Sentence boundary identification |
| 本文献已被 维普 等数据库收录！ |
