ISQNL: interpretable SQL query synthesizer from natural language input

Shubham Milind Phal, Yatish H. R, Tanmay Sanjay Hukkeri, Abhiram Natarajan, Prathika Gonchigar, Deepamala N

Abstract: Databases serve as the forefront for most systems today. Structured query language (SQL) is used to access and manipulate the data stored in a relational database. However, most end users have limited knowledge of SQL and thus face difficulties in accessing such systems. In this paper we describe a novel system (ISQNL) to convert a query provided in Natural Language (English) to an SQL query. By applying several natural language processing techniques ISQNL achieves this conversion without the need for any elaborate schema specific training/modification during setup and is robust enough to handle dynamically changing database states or database schema. ISQNL has demonstrated remarkable accuracy in SQL query synthesis when tested on large sets of natural language input. This paper discusses the methodology and key challenges involved in building ISQNL.