摘要
歧义词的切分是中文分词要面对的数个难题之一,解决好了这个问题就能够有力提升中文分词的正确率。对此,本文简要介绍了汉语分词的概况,并具体分析了当前中文分词技术存在的障碍和介绍了中文分词中的歧义词切分问题,最后在此基础上提出了一种基于多元关系模型的能够有效解决歧义切分的中文分词系统模型并简要分析了这种模型未来的优化方向。
Ambiguity of the word segmentation is the Chinese word segmentation to face one of a number of problems, to solve this problem effectively will be able to upgrade the Chinese word correct rate. In this regard, this article outlined the profile of Chinese word segmentation and specific analysis of the current Chinese word technical obstacles and introduced the Chinese word in the am- biguous word segmentation problem. Finally, on this basis a relationship based on multi-model can be an effective solution to the ambiguity of segmentation Chinese word segmentation system model and a brief analysis of this model of the future directions optimized.
出处
《微计算机信息》
2009年第21期168-169,155,共3页
Control & Automation
关键词
汉语分词
歧义词切分
二元关系模型
Chinese word segmentation
ambiguous word segmentation
Binary model