MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202621080916 A) filed by Symbiosis International Deemed University on June 30, 2026, for An Intelligent Transformer-Based Framework For Bilingual Financial Complaint Classification.
Inventors include Parnika Jain; Srishti Tripathi; Tushar Garg; Mayur Gaikwad; Dr. Aniket K. Shahade; and Dr. Priyanka V. Deshmukh.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: ABSTRACT AN INTELLIGENT TRANSFORMER-BASED FRAMEWORK FOR BILINGUAL FINANCIAL COMPLAINT CLASSIFICATION The present invention discloses an intelligent transformer-based framework (100) for bilingual financial complaint classification. The framework (100) comprises a data acquisition module (110) creating a balanced bilingual English-Hindi corpus through neural machine translation, a bilingual preprocessing module (120) with language-specific pipelines for English (122) and Hindi (124), a feature engineering module (130) generating word-level TF-IDF, character-level TF-IDF, combined bilingual TF-IDF, and XLM-RoBERTa tokenizations, a classification module (140) implementing traditional ML classifiers (142), an ensemble voting classifier (144), and a fine-tuned XLM-RoBERTa classifier (146), and an evaluation module (150). The XLM-RoBERTa classifier captures cross-lingual contextual semantics, achieving superior bilingual complaint classification over frequency-based approaches. [
Disclaimer: Curated by HT Syndication.
