Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations

Relational databases play an important role in business, science, and more.However, many users cannot fully unleash the analytical power of relationaldatabases, because they are not familiar with database languages such as SQL.Many techniques have been proposed to automatically generate SQL from naturallanguage, but they suffer from two issues: (1) they still make many mistakes,particularly for complex queries, and (2) they do not provide a flexible wayfor non-expert users to validate and refine incorrect queries. To address theseissues, we introduce a new interaction mechanism that allows users to directlyedit a step-by-step explanation of a query to fix errors. Our experiments onmultiple datasets, as well as a user study with 24 participants, demonstratethat our approach can achieve better performance than multiple SOTA approaches.Our code and datasets are available at https://github.com/magic-YuanTian/STEPS.