Automatic text summarization based on latent semantic indexing

Automatic summarization is a topic of common concern in computational linguistics and information science, since a computer system of text summarization is considered to be an effective means of processing information resources. A method of text summarization based on latent semantic indexing (LSI), which uses semantic indexing to calculate the sentence similarity, is proposed in this article. It improves the accuracy of sentence similarity calculations and subject delineation, and helps the abstracts generated to cover the documents comprehensively as well as reducing redundancies. The effectiveness of the method is proved by the experimental results. Compared with the traditional keyword-based vector space model method of automatic text summarization, the quality of the abstracts generated was significantly improved.