Automatic Text Summarization by Providing Coverage, Non-Redundancy, and Novelty Using Sentence Graph

The day-to-day growth of online information necessitates intensive research in automatic text summarization (ATS). ATS software produces summary by extracting important from the original text. With help summaries, users can easily read and understand documents interest. Most approaches for used only local properties Moreover, numerous make sentence selection difficult complicated. So this article uses a graph based to utilize structural global It introduces maximal clique (MCBSS) algorithm select non-redundant sentences that cover all concepts input summary. MCBSS finds novel using cliques (MCs). experimental results recall oriented understudy gisting evaluation (ROUGE) on Timeline dataset show proposed work outperforms existing algorithms Bushy Path (BP), Aggregate Similarity (AS), TextRank (TR).