Chinese Text Summarization Based On Thematic Area Detection

Automatic summarization is an active research area in natural language processing. This paper has proposed a special method that produces text summary by detecting thematic areas in Chinese document. The specificity of the method is that the produced summary can both cover many different themes and reduce its redundancy obviously at the same time. In this method, the detection of latent thematic areas is realized by adopting K-medoids clustering method as well as a novel clustering analysis method, which can be used to determine automatically K, the number of clusters.. In addition, a novel parameter, which is known as representation entropy, is used for summarization redundancy evaluation. Experimental results indicate a clear superiority of the proposed method over the traditional non-thematic-area-detection method under the proposed evaluation scheme when dealing with different genres of text documents with free style and flexible theme