Now we often combine syntactic parsing and semantic analyzing when we develop an Chinese-English machine translation system. The base of semantic analyzing is semantic class tagging. This paper designs an algorithm of automatic semantic class tagging which tags words by use of "TongYiCiCiLin". The main idea of the algorithm is that the semantic of most of words can be derived by the semantic of the main constituent word. We did an experiment tagging words in "XianDaiHanYuYuFaXinXiCiDian" and got a machine-readable syntactic-semantic dictionary.
展开▼