基于规则的哈萨克语词干提取算法的研究

摘要

本文提出了一个基于规则的哈萨克语词干提取的一种解决方法.该方法首先找到待切分词的所有可能的词干,然后以带变形词的词典和分类的附加成分表为基础,对找到的若干个词干进行词法分析,最后确定正确的词干.%In this paper, we propose a method of Kazakh word lemmatization by using rule-based analysis.By using our method , first we find all possible stems of the word . Then we apply morphological analysis to the stems by using the table of affix and a list of word variants . At last we get the correct word stem.