Comparative Analysis of Extractive Summarization Using NLP

The step-by-step method of constructing a short, easy-to-read, understandable, and contextual summary of an extensive text document is called text summarization. The principal role is to acquire the correct amount of information within a period. Text reports are finished by humans, which requires experience in space and is also terribly tedious and time-consuming. Along with the advancement of technology, the amount of text data is difficult to understand and is not available in a structured manner due to the larger number of characters. Hence, this is a necessary tool for today. It has been divided into two subparts: text summarization with an abstractive approach, otherwise known as Abstractive Text Summarization (ATS), and the second, text summarization with an extractive approach, otherwise known as Extractive Text Summarization (ETS). In comparison to ATS, the second technique is significantly more manageable and efficient. ETS primarily operates by extracting essential tokens, and in some cases, entire sentences, from the input text document. Consequently, this approach autonomously generates a summary. This work has not only identified novel findings but also suggested cutting-edge techniques and approaches for future researchers in the field, offering valuable insights and practical support.