• Reetik Raj
• Prof Jagadish N
• Himanshu Malik
• Maithili Shetty K
• Aditya Ranjan

We presently live in a data-centric world, where data is produced at a rapid pace. To put things in perspective, 18 billion texts are created per day on various platforms. People today are extremely busy with their daily obligations. How to make content more condensed and accessible without sacrificing its factual meaning is the question that arises. Summarization is the process of selecting important information from a large text by carefully reading the entire text and creating a summary without losing any important details. Research papers and news articles must be summarized, which calls for subject-matter expertise. Automatic text summarization aims to automate this process by reducing long texts into shorter versions. Text summarization has advanced significantly as a result of recent improvements in deep learning methods, particularly neural networks. These models can produce summaries that are comparable to those created by humans because they have been trained on large datasets.

Extractive text summarization, BERT

"EXTRACTING SUMMARY FROM AN ELABORATIVE TEXT USING EXTRACTIVE APPROACH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.i313-i324, May-2023, Available :http://www.jetir.org/papers/JETIR2305871.pdf

"EXTRACTING SUMMARY FROM AN ELABORATIVE TEXT USING EXTRACTIVE APPROACH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppi313-i324, May-2023, Available at : http://www.jetir.org/papers/JETIR2305871.pdf