Automatic database description generation for Text-to-SQL

TL;DR

This paper introduces an automatic method for generating database descriptions to improve Text-to-SQL tasks, employing a dual-process approach that enhances understanding of database schemas and boosts SQL accuracy.

Contribution

It presents a novel dual-process method for automatic database description generation, improving schema understanding and SQL performance in Text-to-SQL tasks.

Findings

Improves SQL accuracy by 0.93% with generated descriptions.

Achieves 37% of human-level performance.

Method is validated on the Bird benchmark.

Abstract

In the context of the Text-to-SQL task, table and column descriptions are crucial for bridging the gap between natural language and database schema. This report proposes a method for automatically generating effective database descriptions when explicit descriptions are unavailable. The proposed method employs a dual-process approach: a coarse-to-fine process, followed by a fine-to-coarse process. The coarse-to-fine approach leverages the inherent knowledge of LLM to guide the understanding process from databases to tables and finally to columns. This approach provides a holistic understanding of the database structure and ensures contextual alignment. Conversely, the fine-to-coarse approach starts at the column level, offering a more accurate and nuanced understanding when stepping back to the table level. Experimental results on the Bird benchmark indicate that using descriptions generated by the proposed improves SQL generation accuracy by 0.93\% compared to not using descriptions, and achieves 37\% of human-level performance. The source code is publicly available at https://github.com/XGenerationLab/XiYan-DBDescGen.