一种基于词典和长度相结合的汉-维句子对齐算法

摘要

A Chinese-Uyghur sentence alignment compound algorithm is presented.It is mainly based on the dictionary,secondly the length of the method.The purpose is to establish a Chinese-Uighur parallel corpus and a practical Chinese-Uyghur sentence alignment system taking the government documents Chinese-Uyghur machine translation as application background.%提出了一种汉-维句子对齐混合算法,它是以基于词典的方法为主、基于长度的方法为辅的一种混合对齐算法.目的在于建立一个以汉文-维文平行语料库及面向政府文献的汉-维机器翻译为应用背景的,实用汉-维句子对齐系统.