Ranking-Based Sentence Retrieval for Text Summarization

Abstract

Text summarization is the technique of extricating notable data from the first content archive. In this procedure, the separated data is produced as a consolidated report and introduced as a clearly expressed rundown. Extractive summarization technique includes choosing critical text or themes from the content and compiling it into a shorter frame. The significance of sentences is chosen in the light of measurable and semantic highlights of sentences. The proposed paper delineates the procedure for text summarization using the Maximal Marginal Relevance (MMR) scoring methodology. The system identifies the most relevant words and selects the sentences, which are similar to the query generated by the words. This automated text summarization algorithm is capable of re-ranking the sentences from the archive, while taking into consideration the semantics and producing a shorter content capable of representing the original content.