Semantic Computation in a Chinese Question-Answering System

This paper introduces a kind of semanticcomputation and presents how to combine it into our ChineseQuestion-Answering (QA) system. Based on twokinds of language resources, Hownet and Cilin, we present anapproach to computing the similarity and relevancy between words. Usingthese results, we can calculate the relevancy between two sentences andthen get the optimal answer for the query in the system. Thecalculation adopts quantitative methods and can be incorporated into QAsystems easily, avoiding some difficulties in conventional NLP (NaturalLanguage Processing) problems. The experiments show that the results are satisfactory.