摘要
中文信息处理的难点很多 ,首先集中在词汇层面上。假如没有词的界限标记 ,怎样解决词的自动切分问题 ;没有形态变化标记 ,计算机难于分析词与词之间句法与语义关系 ;词类划分和兼类情况复杂 ,词性自动判别和标注困难 ;词义的义项。
The difficulty in processing information in Chinese lies in the words as there are no signs of either word boundary or morphological changes for a computer to make out the syntactic or semantic relation between them. In addition, the complexity of classifying parts of speech makes them hard to judge automatically. All these worsen the trouble in clarifying the reference while meaning is analyzed.
关键词
中文信息处理
分词
词类
词义
information process in Chinese
word splitting
parts of speech
denotation
