期刊论文

Chinese Word Segmentation Based on Language Situation

中文

小型微型计算机系统

1000-1220

2005

26

1

129-133

10.3969/j.issn.1000-1220.2005.01.028

本校为其他机构

汉语不同于英语,词之间没有间隔标记.而汉语分词是文本分析的第一步,且存在歧义切分,因此分词问题成为汉语分析的首要难题.通过中文切分过程的本质分析,推导并提出基于马尔可夫链的语境中文切分理论,进而提出一种语境中文分词方法.该方法建立在词法和句法基础上,从语境角度分析歧义字段,提高分词准确率.

Different from English, there are no interval marks between words in C hinese, so it is difficult for word segmentation to identify ambiguous words. Established a theory of Chinese word segmentation with language situation , and proposed a Chinese word segmentation method of language situation. The metho d improves the accuracy of word segmentation, by combini...