机构地区: 清华大学
出 处: 《中文信息学报》 1999年第1期1-8,共8页
摘 要: 汉语在词类这个语言层次上存在着许多歧义结构,这给汉语的自动句法分析带来了难以逾越的障碍。通过寻找汉语语义类之间可能存在的句法关系建立汉语语义关联网,这为用汉语语义知识来解决句法歧义开辟了道路。文章针对具体的汉语歧义结构研究具体的解决办法,从而减少了计算的复杂度。 There are too many syntactic ambiguities in the Chinese, and it is not easy to parse the Chinese sentences automatically only with the Part of Speech (POS) tagging. In order to overcome this barrier we looked for the possible syntactic relations between the semantic clas ses, then built a Chinese Semantic Associate Net (CSAN). Using the CSAN we find a way to solve the problem about the syntactic ambiguities. In this way we do not try to solve all the ambiguities, we only try to solve the certain kind of ambiguities using a special method. So our method is effective.
领 域: [自动化与计算机技术] [自动化与计算机技术]