Natural Language processing based Automatic Text Summarization

Abstract

Text summary is a well-known technique for distilling a document's primary points. Beginning with data extraction from a website link, the recommended approach for text summarizing and keyword extraction continues through a number of steps. It will help with the creation of a machine learning and natural language processing solution to replace the existing product evaluation process (NLP). The next major one is Automatic Text Summarization (ATS), which may simply summarize the source data and provide us with a condensed form that preserves the content and general meaning. Automatic Text Summarization was proposed in the 1950s, but the discipline is still in its infancy. Undirected graphs, weighted graphs, keyword extraction, and sentence extraction are all used in the Text Rank algorithm. In this paper, we will look upon. The proposed solutions for text summarization and keyword extraction passes through a series of processes, beginning with information or data extraction through the website link, eliminating outliers and improper information, and constructing a summary of the extracted information or data. It will assist in the development of a machine learning and natural language processing solution to the traditional product review procedure (NLP). Key Words: Text Summarization, relevant Information, summary, Natural language processing (NLP), Text Summarization.