Research on Automatic Abstracting of WebPages Based on User-Demand

Automatic abstracting is a practical and difficult branch in natural language processing, which becomes an important problem in some domains such as Internet information retrieval. This paper presents a new automatic abstracting method on the basis of traditional method, which adds the sentence weight based on user-demand into the sentence importance. The user-demand consists of the keywords that user queried. The experimental results show that this method can improve the accuracy of searching information.