Converting Human Text into Database Queries Using Natural Language Processing: A Hybrid Approach with Multinomial Logistic Regression and T5

This research introduces a novel system for converting natural language text into structured SQL queries using a hybrid [22] [23] Natural Language Processing (NLP) framework. The system integrates a frontend interface for user input, a Logistic Regression model for query classification, and a T5 Transformer for SQL generation, executed on a relational database. Evaluated on a dataset of 2000 diverse natural language queries, the system achieves 92% accuracy in query classification and 88% in SQL generation, outperforming a rule-based baseline. This work addresses the challenge of enabling non-technical users to interact with databases seamlessly, with applications in data analytics, business automation, and education. Limitations, such as handling multi-table queries and ambiguous inputs, are analyzed, and future enhancements are proposed, including multi-language support and deep learning optimization.