Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge
It addresses the challenge of parsing domain-specific questions into SQL for experts, but it is incremental as it builds on existing text-to-SQL methods with a new knowledge approach.
The paper tackles the problem of knowledge-intensive text-to-SQL parsing, where domain knowledge is needed to convert expert questions into SQL queries, by introducing a new Chinese benchmark called KnowSQL and a framework called ReGrouP that uses formulaic knowledge instead of additional data annotation, resulting in a 28.2% overall improvement on KnowSQL.
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.