Abstract :

In Todays Digital Landscape, Vast Streams Of Unstructured Information Are Generated Through Research Papers, News Articles, Websites, And Legal Records. Manually Digesting This Data Requires Prohibitive Time And Cognitive Effort. To Address This, We Present An AI-Powered MultiModel Text Summarization And Evaluation System With Multilingual Support, A Scalable Web Application That Rapidly Extracts Key Semantic Insights From Extensive Text Repositories. The System Ingests Data Via Three Dynamic Inputs: Direct Plain Text, Document Uploads (PDF/DOCX), And Live Web Text Scraped From User-provided URLs. To Ensure Comprehensive Coverage, The Framework Concurrently Executes Six Independent Extractive Algorithms Frequency-based, TF-IDF, TextRank, LexRank, LSA, And A Hybrid Feature-Based Flagship Model. For Automated Accuracy Verification, The System Computes ROUGE Benchmarks Alongside Semantic BERT Scores. Finally, To Bridge Demographic Barriers, A Neural Machine Translation Pipeline Translates The Summary Outputs Into Regional Indian Languages, Specifically Telugu And Hindi, Without Losing Factual Alignment.

Published:

27-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

1337-1345

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite