A Study Of Question Retrieval Technology In The Chinese Community Question Answering Systems

With the rapid development of Internet technology,information in internet in the present exponential growth,and the rising popularity of the internet gradually changing people’s main way to obtain information. In recent years, the rapid growth of community question answering system has a revolutionary impact on the way of human information acquisition. The information on the network becomes rich and colorful,people also will have trouble on reading at the same time when facing the huge amount of information overload. Therefore, how to quickly and accurately obtain the content of interest in the mass of information has become a new problem faced by people.Currently,Community Question Answering systems have been widely applied. In such systems,the retrieval of similar questions provides the users with answers to the similar questions so as to avoid repeated question submission and help them obtain answers more rapidly. Focusing on question similarity in the community question answering systems,an improved TFIDF algorithm is proposed in this paper.Firstly, the questions are divided into different categories according to the users’ retrieval intention,and the weight of every feature word is adjusted basing on the distribution in the categories; Secondly, the topic words are adopted in the feature words. The experimental results show that in comparison with the traditional TFIDF and the reference algorithm,the retrieval performance is obviously improved with the proposed algorithm.