Text summarization is the process of generating short, fluent, and most importantly accurate summary of a respectively longer text document. The main idea behind automatic text summarization is to be able to find a short subset of the most essential information from the entire set and present it in a human readable format. As online textual data grows, automatic text summarization methods have the potential to be very helpful because more useful information can be read in a short time. For the front end we use html, css and for backend flask. The webapp is built using Flaskandthe modelthat isrunning inthe backendofthiswebapp isbuilt usingspacy library. The extractive technique scans the original d ocument to find the relevant sentences and extracts only that information from it. The abstractive summarization technique interprets the original text before generating the summary. Using state of the art NLP techniques, specifically SBERT and SpaCy, our webapplication allows users to effortlessly generate concise and coherent summaries from extensive textual content. Whether it's news articles, research papers, or any textual data, our tool empowers users to quickly grasp the key insights without the need to read through entire documents. The coretechnology behind our web app is SBERT, a novelsentence embedding model. SBERT captures the semantic relationships between sentences, enabling the generation of informative and context aware summaries. Additionall y, SpaCy, a leading NLP library, aids in linguistic analysis and further improves the qualityof the generated summaries.

Keywords: Summary Generation, Natural Language Processing (NLP), SBERT, Spacy, Text Summarization, Web Application, Information Overloa d, Accuracy, Semantic Analysis.