A Novel Optimized Language-Independent Text Summarization Technique

A substantial amount of textual data is present electronically in several languages. These texts directed the gear to information redundancy. It essential remove this redundancy and decrease reading time these data. Therefore, we need a computerized text summarization technique extract relevant from group documents with correlated subjects. This paper proposes language-independent extractive technique. The proposed presents clustering-based optimization clustering determines main subjects text, while minimizes redundancy, maximizes significance. Experiments are devised evaluated using BillSum dataset for English language, MLSUM German Russian Mawdoo3 Arabic language. experiments ROUGE metrics. results showed effectiveness compared other language-dependent techniques. Our achieved better metrics all utilized datasets. accomplished an F-measure 41.9% Rouge-1, 18.7% Rouge-2, 39.4% Rouge-3, 16.8% Rouge-4 on average three objectives. system also exhibited improvement 26.6%, 35.5%, 34.65%, 31.54% w.r.t. recent model contributed terms metric evaluation. model’s performance higher than models, especially ROUGE_2 which bi-gram matching.