Using Database Rule for Weak Supervised Text-to-SQL Generation
This addresses the problem of generating SQL queries from natural language without requiring labeled SQL logic forms, which is useful for database users and developers, though it appears incremental as it builds on existing weak supervision approaches.
The paper tackles text-to-SQL generation with weak supervision by proposing Rule-SQL, which uses database rules to explore SQL queries from questions and answers, then trains a BERT-based model; it outperforms strong fully supervised baselines on WikiSQL and is comparable to state-of-the-art weakly supervised methods.
We present a simple way to do the task of text-to-SQL problem with weak supervision. We call it Rule-SQL. Given the question and the answer from the database table without the SQL logic form, Rule-SQL use the rules based on table column names and question string for the SQL exploration first and then use the explored SQL for supervised training. We design several rules for reducing the exploration search space. For the deep model, we leverage BERT for the representation layer and separate the model to SELECT, AGG and WHERE parts. The experiment result on WikiSQL outperforms the strong baseline of full supervision and is comparable to the start-of-the-art weak supervised mothods.