A Web-based Chinese automatic question answering system

Question answering system can give users precise answer to the question presented in natural language. Currently, most of question answering system use large scaled corpus as knowledge base to extract answer. However, abundant source of Web provides another ideal knowledge origin for question answering system. The research result shows that using Web data resource as database for question answering system can get good result about simply and fact-based question. This paper presents an answer extraction method which based on the calculation of sentence similarity between question and answer. We also realize a Web-based Chinese QA system. This system only utilizes the "snippet" in result returned by Web search engine as data resource for answer extraction. The experiment result indicates that the system can get prominent results for person, time and number type question, the MRR of all questions is 0.51.