义类自动标注方法的研究

句法分析不能满足汉语分析的需要,句法和语义相结合的分析方法适用于汉语分析。分析的基础要有一部语法语义词典。目前的机读词典多是语法词典,因而需要在语法词典中加入词的语义信息。《同义词词林》是一部较好的义类词典,但没有语法信息,可以《同义词词林》的分类体系对语法词典进行义类标注,得到语法语义词典。这一过程中有不一致的情况,特别地,对《同义词词林》中未收录的词就不能直接标注义类。本文采用《同义词词林》的分类体系,研究设计了一个汉语词自动义类标注算法,对北大《现代汉语语法信息词典》进行自动义类标注。实验结果较为满意,得到91%的准确率。

Research of Automatic Semantic Class Tagging

During the development of Machine Translation System ,We need a semantic class dictionary to do semantic analyzing. This paper designs an arithmetic of semantic class automatic tagging which tags words by use of“TongYiCiCiLin”. The idea of the arithmetic is that the meaning of most of words can be represented by the main component of words. We did an experiment tagging words in ”XianDaiHanYuYuFaXinXiCiDian”and got a machine-readable syntactic-semantic dictionary.