Knowledge Base Construction for Knowledge-Augmented Text-to-SQL

TL;DR

This paper introduces a comprehensive knowledge base construction method for text-to-SQL tasks, enhancing the accuracy of SQL generation by grounding queries in a reusable, domain-agnostic knowledge source, outperforming existing approaches.

Contribution

It proposes a novel, comprehensive knowledge base construction approach that leverages all available questions and schemas, improving generalization and accuracy in text-to-SQL translation.

Findings

Outperforms relevant baselines on multiple datasets

Effective in both overlapping and non-overlapping database scenarios

Enhances SQL accuracy by grounding in a knowledge base

Abstract

Text-to-SQL aims to translate natural language queries into SQL statements, which is practical as it enables anyone to easily retrieve the desired information from databases. Recently, many existing approaches tackle this problem with Large Language Models (LLMs), leveraging their strong capability in understanding user queries and generating corresponding SQL code. Yet, the parametric knowledge in LLMs might be limited to covering all the diverse and domain-specific queries that require grounding in various database schemas, which makes generated SQLs less accurate oftentimes. To tackle this, we propose constructing the knowledge base for text-to-SQL, a foundational source of knowledge, from which we retrieve and generate the necessary knowledge for given queries. In particular, unlike existing approaches that either manually annotate knowledge or generate only a few pieces of knowledge for each query, our knowledge base is comprehensive, which is constructed based on a combination of all the available questions and their associated database schemas along with their relevant knowledge, and can be reused for unseen databases from different datasets and domains. We validate our approach on multiple text-to-SQL datasets, considering both the overlapping and non-overlapping database scenarios, where it outperforms relevant baselines substantially.