• Chitrani Somkuwar
• Achal Lute
• Tanuja Kadwe
• Bhavik Balpande
• Utkarsh Zode

Text summarization is a powerful solution to the overwhelming amount of textual data available to us. By using NLP techniques, algorithms can analyze and distill large amounts of text into concise summaries. Extractive summarization involves selecting relevant sentences from the original text, while abstractive summarization generates a summary that captures the essence of the information. While abstractive summarization can be more challenging, it often produces more comprehensive and readable summaries. As NLP techniques continue to evolve, we can expect more accurate text summarization solutions to emerge. Our tool offers a comprehensive view of the abstractive technique and allows users to perform summarization using pre-trained models. We have used the Text to text transformer (t5) base model which is a Natural Language Processing (NLP) Model implemented in the Transformer library, using the Python programming language. We have also implemented a summary range feature and the ability to copy the summarized text for future use.

Keywords: Natural Language Processing (NLP), text summarization, abstractive summarization.

"Designing a system using NLP for summarizing a text and retaining crucial points in a text", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.a503-a508, May-2023, Available :http://www.jetir.org/papers/JETIR2305069.pdf

"Designing a system using NLP for summarizing a text and retaining crucial points in a text", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppa503-a508, May-2023, Available at : http://www.jetir.org/papers/JETIR2305069.pdf