TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation

TL;DR

TypeSQL is a neural model that converts natural language questions into SQL queries by leveraging type information and database content, significantly improving accuracy and efficiency over previous methods.

Contribution

This paper introduces TypeSQL, a novel slot filling approach that incorporates type and content information to enhance natural language to SQL translation.

Findings

Outperforms previous state-of-the-art by 5.5% on WikiSQL.

Achieves 82.6% accuracy, a 17.5% improvement with content access.

Reduces training time compared to prior models.

Abstract

Interacting with relational databases through natural language helps users of any background easily query and analyze a vast amount of data. This requires a system that understands users' questions and converts them to SQL queries automatically. In this paper we present a novel approach, TypeSQL, which views this problem as a slot filling task. Additionally, TypeSQL utilizes type information to better understand rare entities and numbers in natural language questions. We test this idea on the WikiSQL dataset and outperform the prior state-of-the-art by 5.5% in much less time. We also show that accessing the content of databases can significantly improve the performance when users' queries are not well-formed. TypeSQL gets 82.6% accuracy, a 17.5% absolute improvement compared to the previous content-sensitive model.