• JAYA VERMA
• MIHIR BARI
• SWETA KUMARI
• YASH MESTRY
• POONAM SONAR

Today, information overload is a reality due to the rapid emergence and evolution of new technologies. Although readers can easily identify a text's readability by its abstract, most information is not written in an abstract. This project aims to simplify articles so that everyone can understand them. Text summarization is a process that can be used in web pages and social media applications to identify the trends in a given topic. In this project, we will use pre-trained Natural Language Processing models such as Pegasus, BERT, and Simple T5. These models can perform various tasks, and they can also be used to analyze the results of a study. The aim of the project is to fine-tune pre-trained models in order to increase their performance. Pegasus, Bert, and a simple T5 model have all been fine-tuned by us . These models were trained on a large corpus of text and fine-tuned on a samsum dataset. Evaluating the performance of different models can help determine which one is best at producing succinct, accurate summaries. The evaluation will be based on established metrics such ROUGE scores, and the findings will be examined to identify each model’s advantages and disadvantages. The goal of this research is to improve text summarization’s capabilities and to provide light on the efficiency of different models for this job

Text Summarization; Abstractive Text Summarization; NLP; Pegasus; BERT; Simple T5; Rough Score.

"Text Summarization using Pre-trained model (Pegasus, Bert, Simple-T5)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.j39-j46, July-2023, Available :http://www.jetir.org/papers/JETIR2307906.pdf

"Text Summarization using Pre-trained model (Pegasus, Bert, Simple-T5)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppj39-j46, July-2023, Available at : http://www.jetir.org/papers/JETIR2307906.pdf