An Interactive Approach to Generating SQL Queries from Natural Language

Abstract

In this thesis, we contribute nalini, an natural-language based interactive interface for SQL query generation. Motivated by a lack of usability of existing systems, nalini was built with the intention of using it for complex query generation. The interface allows users to use a natural language and mathematical operations with a minimal structure. We evaluated nalini with a first-use study with five participants, where participants were asked to generate queries from the TPC-H decision support benchmark. Our study showed that users were able to use nalini to generate complex queries, and points to promising areas of future work.