Automatic text summarization based on textual cohesion

This paper presents two different algorithms that derive the cohesion structure in the form of lexical chains from two kinds of language resources HowNet and TongYiCiCiLin. The research that connects the cohesion structure of a text to the derivation of its summary is displayed. A novel model Of automatic text summarization is devised, based on the data provided by lexical chains from original texts. Moreover, the construction rules of lexical chains are modified according to characteristics of the knowledge database in order to be more suitable for Chinese summarization. Evaluation results show that high quality indicative summaries are produced from Chinese texts.