Quantum mechanics

Natural language

Ecology

Biology

Computational linguistics

China

Archaeology

Search engine

Economics

Zhàng

Computer science

Natural language processing

Type (biology)

Web search query

Physics

Database

Task (project management)

Management

Relational database

Query by Example

Artificial intelligence

Information retrieval

Programming language

Volume (thermodynamics)

History

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 wellformed.TYPESQL gets 82.6% accuracy, a 17.5% absolute improvement compared to the previous content-sensitive model.

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