Automated persian text summarization based lexical chain and graph using of farsnet

Automatic document summarization technology is evolving and can provide a solusion to the problems additional information. Today, The summary document, plays an important role in recovery. Document summarization process that compact version automatically creates a certain document and provides useful information to user; The lexical cohesion structure of the text can be exploited to determine the importance of a sentence/phrase. Lexical chains and useful tools to analysis the lexical cohesion structure in a text. In this paper, the problem ambiguity has been as one of challenges natural language processing , As disambiguate sense words, summary can be produced closer to human summaries. The suggested algorithm is based on knowledge; And the use of lexical chain and graph methods. The suggested method, at first find the true sense of any word; Then constructs the lexical chains, remove lexical chains that less score than other, detects topics roughly from lexical chains, segments the text with respect to the topics and selects the most important sentence. The experimental results on a pasokh dataset show that suggested method can improve the performance compared to ijaz and farsisum Persian text summarizers.

Automated persian text summarization based lexical chain and graph using of farsnet Keywords:

sentence Extraction , Persian language processing , text summarization , Extraction summary , data mining , word sense disambiguation , text mining