Natural SQL: Making SQL Easier to Infer from Natural Language Specifications

TL;DR

This paper introduces Natural SQL (NatSQL), an intermediate representation that simplifies SQL queries to improve natural language to SQL translation, leading to better performance on complex benchmarks and enabling existing models to generate executable SQL.

Contribution

The paper proposes NatSQL, a simplified SQL IR that enhances text-to-SQL translation accuracy and compatibility with existing models, especially on complex queries.

Findings

NatSQL outperforms other IRs on the Spider benchmark.

NatSQL significantly improves state-of-the-art models' performance.

NatSQL enables non-executable models to generate executable SQL with higher accuracy.

Abstract

Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specifically, NatSQL preserves the core functionalities of SQL, while it simplifies the queries as follows: (1) dispensing with operators and keywords such as GROUP BY, HAVING, FROM, JOIN ON, which are usually hard to find counterparts for in the text descriptions; (2) removing the need for nested subqueries and set operators; and (3) making schema linking easier by reducing the required number of schema items. On Spider, a challenging text-to-SQL benchmark that contains complex and nested SQL queries, we demonstrate that NatSQL outperforms other IRs, and significantly improves the performance of several previous SOTA models. Furthermore, for existing models that do not support executable SQL generation, NatSQL easily enables them to generate executable SQL queries, and achieves the new state-of-the-art execution accuracy.