Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge

TL;DR

This paper introduces a new approach for knowledge-intensive text-to-SQL parsing using a formulaic knowledge bank, demonstrating significant improvements on a newly created Chinese benchmark.

Contribution

The paper presents a novel framework leveraging formulaic knowledge for text-to-SQL parsing, along with a new Chinese benchmark dataset, KnowSQL.

Findings

28.2% overall improvement on KnowSQL

Effective use of formulaic knowledge in parsing

Introduction of a new Chinese domain-specific benchmark

Abstract

In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables. We formalize this scenario by building a new Chinese benchmark KnowSQL consisting of domain-specific questions covering various domains. We then address this problem by presenting formulaic knowledge, rather than by annotating additional data examples. More concretely, we construct a formulaic knowledge bank as a domain knowledge base and propose a framework (ReGrouP) to leverage this formulaic knowledge during parsing. Experiments using ReGrouP demonstrate a significant 28.2% improvement overall on KnowSQL.