MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202621080941 A) filed by Symbiosis International Deemed University on June 30, 2026, for Scalable Multilingual News Summarization And Categorization System Using Nlp.
Inventors include Dhruvi Ramaiya; Dr. Aniket K. Shahade; Dr. Priyanka V. Deshmukh; Dr. Shruti Patil; and Dr. Ketan Kotecha.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: ABSTRACT SCALABLE MULTILINGUAL NEWS SUMMARIZATION AND CATEGORIZATION SYSTEM USING NLP The present invention discloses a scalable multilingual news summarization and categorization system (100) for processing news articles through an end-to-end NLP pipeline. The system (100) comprises an input handling module (110) accepting raw text and web URLs with web content extraction, a language processing module (120) with automatic language detection and translation, a classification module (130) employing TF-IDF vectorization unit (132) and Naive Bayes classifier unit (134) achieving 98 percent accuracy across four categories, a summarization module (140) with text chunking unit (142) and T5 transformer unit (144) for chunk-based abstractive summarization with summary merging unit (146), and a multilingual output module (150) delivering categorized summaries in Hindi or English. The system achieves macro-averaged F1- score of 0.98 with 9 percent improvement over baseline methods. [
Disclaimer: Curated by HT Syndication.
