Publication

Abstract : This paper is about a comparative analysis of two most commonly used text summarization methods used in the current generation, abstractive summarization and extractive summarization method within the domain of Natural Language Processing (NLP), a field that is growing in the area of modern processing of information. Summarization methods are essential to filter large textual data into small and informative representations, basically in real-world applications where regular insights are of the utmost importance. Abstractive methods generate new sentences which capture the original core of the text, whereas extractive methods select and combine important sentences or data. Applying innovative NLP methods and actual data, the comparative study examines various parameters such as the ability to withstand variations in input, efficiency, and the ability to explain the output of the trained model for both approaches. By proper analysis of the development of data and applying advanced scientific techniques for analysis, this research offers important insights into the effectiveness of abstractive and extractive summarization methods in real-time cases.