AI-Powered Document Summarization: Existing Technologies, Challenges, Proposed Solutions, and Future Prospects

The fast-paced rise in the magnitude of digital text brings the urgent requirement for intelligent summarization systems that can adapt to diverse document types and domainspecific language. This paper presents a context-aware system for multi-model text summarization that internally uses state-of-theart Transformer models, namely, BART, PEGASUS, and FLANT5. In classifying documents and analyzing content complexity, it selects the most appropriate model to generate accurate and coherent summaries with respect to the type of document and complexity of contents. Preprocessing methods target specialized elements like code blocks, equations, citations, and technical terms that are detrimental to output quality. The web-based architecture is built on a stack comprising React, Node.js, and MongoDB allowing for scale and ease of access from a user standpoint. For long inputs, performance test results demonstrate an accuracy of 85-90% with a turnaround time of less than 10 seconds. This work presents the architecture and gives insight into the operational procedures, thereby outlining its usefulness in academic, technical, and media domains. It thus strongly affirms the usefulness of adaptive summarization in handling complex domain-rich digital content.

• Publication year

  2025

• Venue

  2025 OITS International Conference on Information Technology (OCIT)

• Publication date

  2025-12-18

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/OCIT66168.2025.11400475
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• AI-driven Generation of News Summaries Leveraging GPT and Pegasus Summarizer for Efficient Information Extraction

  2024cited by this paper
• A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models

  2024cited by this paper
• Abstractive Summarizers Become Emotional on News Summarization

  2024cited by this paper
• Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT Models

  2023cited by this paper
• CoVShorts: News Summarization Application Based on Deep NLP Transformers for SARS-CoV-2

  2021cited by this paper
• SHEG: summarization and headline generation of news articles using deep learning

  2020cited by this paper
• Automatic News Article Summarization

  2018cited by this paper
• Automatic text summarization of news articles

  2017cited by this paper
• An Effective Approach for News Article Summarization

  2013cited by this paper
• A trainable document summarizer

  1995cited by this paper

• No citing papers are available for this paper.