Presented at SPUDC 2024 (Simposio en Programación e Intelixencia Artificial), the annual research symposium at Universidade da Coruña.
This paper introduced a conversational interface that allows non-technical users to interact with relational databases using natural language. The system translates user questions into SQL queries, executes them, and verbalizes the results — removing the barrier of SQL knowledge for data access.
The study benchmarked four leading language model backends using human-centric evaluation criteria, providing a practical baseline for conversational database access in real organizational workflows.