ADVANCEMENT IN AUTOMATIC TEXT SUMMARIZATION

Abstract

In the last ten years, there has been a notable surge in the fields of Artificial Intelligence (AI), Machine Learning (ML), and Data Science, offering several prospects across various sectors like healthcare, banking, and transportation. Particularly, the area of Natural Within AI and ML, the field of language processing (NLP) has advanced significantly. NLP is the study and application of machine learning to human language. Text summarization is a popular application because it allows computers to summarise long texts into short summaries. The use of several extractive text summarising methods, including as BERT, GPT-2, KLsummerizer, Luhn, LEX, and Word Rank, is highlighted in this research. The resulting extractive summaries are then assessed using Rouge Score, BERT Score, and Mover Score— three different scoring techniques—against human-generatedThe extractive summaries that are produced are then assessed using Rouge Score, BERT Score, and Mover Score in comparison to human-generated summaries. Through this study, we evaluate the quality of the generated summaries and show how effective these techniques are in producing summaries by comparing them to human-produced summaries using the predetermined scoring standards.