基于语义计算的语句相关度研究

该文在中文问题回答系统中引入了语义计算。基于《词林》和hownet两种语言资源,提出计算词与词之间的相似度和相关度,然后得到语句间的相关度,系统通过对语句相关度的比较从而得到查询问题的最优答案。该方法采用了定量计算,易于结合到QA系统中,同时避免了很多传统的自然语言处理问题。试验结果表明该方法是有效的。

Research of Relevancy between Sentences Based on Semantic Computation

This paper introduces semantic computation into our Chinese Question-Answering system.Based on two kinds of language resources Cilin and hownet,this paper presents an approach to compute the similarity and relevancy between words.Using these results,the relevancy between two sentences can be calculate and the optimal answer for the query can be get in the system.The method adopts quantitative methods and can be incorporated into QA systems easily,avoiding some difficulties in conventional NLP problems.Finally some examples are presented to show that the results are satisfying.