Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages
This work addresses the challenge for non-experts interacting with databases by enhancing text-to-SQL accuracy, though it is incremental as it builds on existing prompt-based methods with a novel pivot approach.
The paper tackles the problem of low accuracy in text-to-SQL conversion due to the semantic gap between natural language and SQL by using Python as a pivot language to provide fine-grained guidance, resulting in improvements such as a 3.20 increase in execution accuracy and a 4.55 higher efficiency score compared to baselines.
Text-to-SQL transforms the user queries from natural language to executable SQL programs, enabling non-experts to interact with complex databases. Existing prompt-based methods craft meticulous text guidelines and examples to facilitate SQL generation, but their accuracy is hindered by the large semantic gap between the texts and the low-resource SQL programs. In this work, we propose Pi-SQL, which incorporates the high-resource Python program as a pivot to bridge between the natural language query and SQL program. In particular, Pi-SQL first generates Python programs that provide fine-grained step-by-step guidelines in their code blocks or comments, and then produces an SQL program following the guidance of each Python program. The final SQL program matches the reference Python program's query results and, through selection from candidates generated by different strategies, achieves superior execution speed, with a reward-based valid efficiency score up to 4.55 higher than the best-performing baseline. Extensive experiments demonstrate the effectiveness of Pi-SQL, which improves the execution accuracy of the best-performing baseline by up to 3.20.