Research On Internet Based Chinese Question-Answering System

As Internet popularizes, more and more information are available online, providing a huge amount of resources for people. However, with the overwhelming information, people find it very difficult to find the information they need quickly and accurately. There are some search engines that can help people to search for needed information, but they are far from being satisfactory. Question answering (QA) technology is developed to meet people's demand. The inputs of search engines are combinations of keywords, while QA systems enable users to input a question in natural languages. The outputs of search engines are some related web pages, while QA systems can give users concise and accurate answers. By using QA systems, users can find the information they need conveniently, quickly and accurately.An Internet based Chinese QA system is constructed based on the English QA system. The implementation of each component is described in detail. In question analysis module, a rule-based method for question classification is used. In candidate sentences selection module, the methods we used to compute the similarity between sentences and query are N-gram modal and Vector Space modal. In answer extraction module HMM based Named Entity Recognition is used.At last this paper introduce the evaluation of the system. The results of the experiments show that although the system presented here is primitive, the methods used in English QA system can be applied in Chinese QA system likewise.