Recent Advances in SQL Query Generation: A Survey
It addresses the problem of providing a natural language interface to relational databases for users, but it is incremental as it surveys existing work without introducing new methods.
This survey overviews recent methods and models for generating SQL queries from natural language, covering various architectures like convolutional and recurrent neural networks, and discusses datasets and evaluation metrics such as execution and logical form accuracy.
Natural language is hypothetically the best user interface for many domains. However, general models that provide an interface between natural language and any other domain still do not exist. Providing natural language interface to relational databases could possibly attract a vast majority of users that are or are not proficient with query languages. With the rise of deep learning techniques, there is extensive ongoing research in designing a suitable natural language interface to relational databases. This survey aims to overview some of the latest methods and models proposed in the area of SQL query generation from natural language. We describe models with various architectures such as convolutional neural networks, recurrent neural networks, pointer networks, reinforcement learning, etc. Several datasets intended to address the problem of SQL query generation are interpreted and briefly overviewed. In the end, evaluation metrics utilized in the field are presented mainly as a combination of execution accuracy and logical form accuracy.