Research on Topic Segmentation of Chinese Text Based on Lexical Chain

Migration of the central idea of sub-theme content sufficiently reflects development of the idea of an article. The main purpose of topic segmentation is to identify the boundary between sub-themes. Accurate topic segmentation is of great value to many natural language processing applications such as automatic summarization, request-answering system etc. This paper proposes a method of topic segmentation of Chinese text based on lexical chain, and shows the efficiency and accuracy of the method through many experiments. At last, it put forwards the disadvantages and future prospect of the approach.