Publication Details

Abstract

Document summarization plays a significant role in reducing the effort required to understand large volumes of textual information. Traditional summarization methods rely on rule-based or statistical approaches, which often fail to capture contextual meaning and produce less accurate results. To overcome these limitations, an AI-based document summarization system is proposed that automatically generates concise and meaningful summaries from input documents. The system utilizes transformer-based deep learning models to improve summarization accuracy and contextual understanding. It also integrates Optical Character Recognition (OCR) to extract text from images, along with multilingual translation and text-to-speech modules to enhance accessibility. Data preprocessing techniques are applied to handle different input formats and improve model performance. The system is implemented using modern deep learning frameworks and supports real-time processing of documents. Experimental results demonstrate that the proposed system effectively reduces document length while preserving key information. Overall, the system provides an efficient, scalable, and user-friendly solution for document summarization with improved accessibility features.