基于规则的维吾尔语对偶词识别算法研究  

Research on Rule-Based Recognition Algorithm of Uyghur Antithetic Words

作　　者：扎依达.木沙 吐尔根.依布拉音 

机构地区：[1]新疆大学信息科学与工程学院,新疆乌鲁木齐830046

出　　处：《新疆大学学报（自然科学版）》2009年第2期221-226,共6页Journal of Xinjiang University(Natural Science Edition)

基　　金：国家自然科学基金项目(60663006);新疆维吾尔自治区高新技术研究与发展计划项目(200712109)

摘　　要：维吾尔语对偶词的自动识别是维吾尔语自然语言处理中的一项基础性工作.维吾尔语对偶词的自动识别是维吾尔语自动分词的难点之一,也是一个重点.在维吾尔语中,内部成分平等连接而形成的词汇单位叫做对偶词.本文首先介绍了对偶词的基本概念和特征,然后分析了维吾尔语对偶词的结构特征和结合规则.在字符串匹配算法的基础上,提出了一种基于规则的维吾尔语对偶词的识别算法,并通过试验证明了该算法的正确性.Automatic recognition of Uyghur antithetic words is the basic work of Uyghur natural language processing. It is also one of the most difficult and important problems in Uyghur word tokenization. In Uyghur, there are some kinds of words that their components equally connect each other and form a lexical unit, this kinds of words are called antithetic words. Firstly, this article introduced the basic concepts and feature of Uyghur antithetic words, analysed the structure and combination rules of Uyghur antithetic words. A rule-based Uyghur Antithetic Words Recognition Algorithm based on the String Matching Algorithm is presented, also experiment shows the correctness of this algorithm.

关 键 词：维吾尔语 对偶词 规则 识别 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]