Based On Latent Semantic Analysis About The University Of Chinese Question Answering System

Question Answering System is a computer program which to find the exact answer to the user's natural-language query in a large document repository. We design a College General Conditions Chinese Question Answering System based on LSA(QASYS). It makes the retrieval about the college conditions quickly and simple.QASYS retrieval information overcome a fundamental problem of synonym and polysemy in the conventional retrieval system by LSA.There are three modules in this system:The document repository pre-processing module including Web pages crawlering, HTML format filtering , segmentation and Tagging etc. Finally, we receive a term-document matrix by computer the word frequency.This matrix is then analyzed by SVD to derive our particular latent semantic structure model for later document retrieval and passage retrieval.Question analysis module is important to QA system. Given a question, the system generates a number of weighted rewrite strings. And then, transform the query into a vector by those weighted rewrite strings. In this module, lay emphasis on question classification. System classifies a query into the predefined classes based on the type of answer it is looking for, then use the question types to identify a candidate answer within the retrieved sentences.Answer extraction module including:document retrieval, passage retrieval and answer matching. System provide a varying method to calculate weight and sort the answer by the weight. Finally, the answer been restricted within 50 words long and returned to user.