论文部分内容阅读
即对词根和词缀以维吾尔语语法为基础,作出语法和词汇定义,通过现代信息处理事业广泛运用的机器学习方法,计算词缀和词根聚合概率,将概率意义为主,自动推断文本中的单词聚合失误和符合词根的词缀自动选择原理。
That is to say, grammar and vocabulary are defined based on Uyghur grammar for stems and affixes. Machine learning methods widely used in modern information processing are used to calculate the probability of affix and root polymerization, and the probability is the main factor to automatically infer the aggregation of words in the text Error and stemming affix automatic selection principle.