摘要
40 000 new entries are added to CiLin in knowledge engineering. Statistics are presented about the sense ambiguity of Chinese words in CiLin. An automatic solution is proposed for the problem of Chinese sense disambiguation, which utilizes the heuristics of part-of-speech tagging and Nave Bayes classification based on a partially disambiguated corpus.
基金
国家高技术研究发展计划(863计划)
