MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511104649 A) filed by Lovely Professional University, Phagwara, Punjab, on Oct. 30, 2025, for 'explainable text classification system.'
Inventor(s) include Dr. Gaurav Sethi; Dr. Varun Kumar; Dr. Suresh Kumar; and Dr. Amit Dutt.
The application for the patent was published on Dec. 12, under issue no. 50/2025.
According to the abstract released by the Intellectual Property India: "An explainable text classification system, comprises of a preprocessing module 101 configured to refine text data using natural language processing techniques by eliminating elements contributing minimal semantic value, a dataset balancing module 102 adapted to apply a synthetic minority oversampling technique for handling class imbalance, a validation module 103 configured to employ repeated stratified K-Fold cross-validation for improving model robustness and preventing overfitting, and a classification and explanation module 104 comprising a plurality of machine learning and hybrid models integrated with a local interpretable model-agnostic explanations framework for providing interpretability of classification results, the system enhances performance across multiple domains, achieves superior accuracy, precision, recall, and F1-score."
Disclaimer: Curated by HT Syndication.
