The design and implementation of chinese question and answering system

Abstract

Information retrieval has been proven effective in discovering specific passages within large collections of documents in response to a user query. Users frequently obtain brief answers to specific questions instead of obtaining the whole documents. The QA system can process the question statement in Chinese natural language fashion and find out the implicit intention of the user query, This study proposes a Chinese Question Answering system based on HowNet and Autotag. The experiment collected 900 Chinese News items from www.chinatimes.com and presented an excellent MRR (Mean Reciprocal Rate) value at 0.84.