论文部分内容阅读
改革开放后,新疆与国内以及国际交往越来越频繁。新疆少数民族人名汉字音译转写缺少统一标准,维吾尔人名汉字音译转写时,在户口上是一种写法,在身份证上另一种写法,在护照上更不一样的用字写法,机票、汇款单等又是一种写法。为解决这些问题,前人作了研究并取得了一定成果以及使用维吾尔人名汉语音译撰写系统来规范维吾尔人名汉语音译。但是这些成果正确率只有52%。利用规则和维吾尔人名特征相结合的方法,提高系统自动维吾尔人名汉语音译正确率30%。介绍该领域研究进展,通论维吾尔音节切分与维吾尔人名特征相结合方法。陈述基于字形的DOM音译框架解决的问题,介绍基于音节切分的维吾尔人名汉字音译转写的实现方法,给出了实验结果与分析。
After the reform and opening up, Xinjiang has become more frequent with its domestic and international counterparts. There is a lack of uniform standards for the transliteration of Chinese characters in ethnic minorities in Xinjiang. When transliterating Uyghur names and transliterations of Chinese characters, it is a method of writing on the account. Another way of writing is on the identity cards. In the passport, it is even more difficult to use words, air tickets, Remittance is another way of writing. In order to solve these problems, our predecessors have made some research and achieved some achievements as well as using the Uighur Chinese transliteration writing system to regulate the Uyghur Chinese transliteration. However, the correct rate of these results is only 52%. By using the combination of rules and Uyghur names, the correct rate of Chinese Uyghur Chinese transliteration by 30% is improved. The research progress in this area is introduced, and the combination of Uyghur syllable segmentation and Uyghur name features is discussed. This paper describes the problems that are solved by the orthographic DOM transliteration framework and introduces the realization method of transliteration of Uighur Chinese characters based on syllable segmentation. The experimental results and analysis are given.