"What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQL
This addresses the challenge of improving text-to-SQL systems for database users by making them more robust through human-in-the-loop interaction, though it is incremental as it builds on existing parsers.
The paper tackles the problem of text-to-SQL parsers struggling with real-world deployment due to difficulty understanding natural language questions by introducing a parser-independent interactive approach (PIIA) that uses multi-choice questions to interact with users, enhancing performance on WikiSQL and Spider datasets with limited interaction turns.
In Natural Language Interfaces to Databases systems, the text-to-SQL technique allows users to query databases by using natural language questions. Though significant progress in this area has been made recently, most parsers may fall short when they are deployed in real systems. One main reason stems from the difficulty of fully understanding the users' natural language questions. In this paper, we include human in the loop and present a novel parser-independent interactive approach (PIIA) that interacts with users using multi-choice questions and can easily work with arbitrary parsers. Experiments were conducted on two cross-domain datasets, the WikiSQL and the more complex Spider, with five state-of-the-art parsers. These demonstrated that PIIA is capable of enhancing the text-to-SQL performance with limited interaction turns by using both simulation and human evaluation.