Extractive Article Summarization Using Integrated TextRank and BM25+ Algorithm

The quantity of textual data on the internet is growing exponentially, and it very tough task to obtain important relevant information from it. An efficient effective method required that provides a concise summary an article. This can be achieved by usage automatic text summarization. In this research, authors suggested approach for summarization where extractive generated methodology was modified integrating normalized similarity matrix both BM25+ conventional TextRank algorithm, which resulted in improvised results. A graph taking sentences article as nodes edge weights score between two sentences. maximum rank are selected, extracted. Empirical evaluation proposed analyzed compared with baseline methods viz. term frequency–inverse document frequency (TF–IDF) cosine, longest common consequence (LCS), precision, recall, F1 criteria. ROUGE-1, ROUGE-2, ROUGE-L scores were calculated all methods. outcomes demonstrate efficiently summarize any irrespective category belongs to.