TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation
This work addresses the challenge of enabling users of any background to query relational databases easily, representing an incremental advance with specific performance gains.
The paper tackles the problem of converting natural language questions to SQL queries for database interaction, achieving a 5.5% improvement over prior state-of-the-art on the WikiSQL dataset and 82.6% accuracy with a 17.5% absolute gain over previous content-sensitive models.
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.