Year: 2025
Type: article
Abstract: Withtheexponentialincreaseindigitalinformation, the challenge of information overload has become critical. Automatic Text Summarization (ATS) offers a solution by distilling keyinformationfromlargetextsintoconcisesummaries.ThispaperexploresATSmethodologies,focusingonclassificationsbased on input type, purpose, and output type. It provides a detailed analysis of Extractive Text Summarization (ETS), Abstractive Text Summarization (ABS), and Hybrid Text Summarization (HTS). Our implemented ATS system achieves an impressive 90% accuracy, highlighting its effectiveness and reliability. By comparing techniques, datasets, and evaluation metrics, this paper identifies strengths and limitations while proposing future improvements in ATS systems.
Author: Mayank Gangadhar Warkade
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4411761770