Natural Language Based SQL Query Verification Against Relational Schema

Abstract

Writing SQL queries for database is a complex and skill requiring task especially for the new users. The situation becomes more critical when a low skilled person want to access and analyze his data from a relational database. These scenarios require expertise and skills in terms of understanding and writing the accurate and functional queries. However, these complex tasks can be simplified by providing an easy interface to the users. In order to resolve all such issues, automated software tool is needed, which facilitates both users and software engineers. In this paper we present a novel approach with name Que-Gen (Query Generator) that generates SQL queries based on the specification provided in National English Language. Users need to write the requirements in simple English in a few statements. After a semantic analysis and mapping of the associated information. Que-Gen generates the intended SQL queries that can be executed directly on the database. An experimental study has been conducted to analyze the performance and the accuracy of the purposed tool.