ServiceNow Research

DuoRAT: Towards Simpler Text-to-SQL Models

Abstract

Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have proposed increasingly sophisticated solutions to the problem. Contrary to this trend, in this paper we focus on simplifications. We begin by building DuoRAT, a re-implementation of the state-of-the-art RAT-SQL model that unlike RAT-SQL is using only relation-aware or vanilla transformers as the building blocks. We perform several ablation experiments using DuoRAT as the baseline model. Our experiments confirm the usefulness of some techniques and point out the redundancy of others, including structural SQL features and features that link the question with the schema.

Publication
North American Chapter of the Association for Computational Linguistics (NAACL)
Torsten Scholak
Torsten Scholak
Research Scientist

Research Scientist at Human Machine Interaction Through Language located at Montreal, QC, Canada.

Raymond Li
Raymond Li
AI Developer

AI Developer at Large Language Models Lab located at Montreal, QC, Canada.

Dzmitry Bahdanau
Dzmitry Bahdanau
Research Lead

Research Lead at Human Machine Interaction Through Language located at Montreal, QC, Canada.

Harm de Vries
Harm de Vries
Research Lead

Research Lead at Large Language Models Lab located at Amsterdam, Holland.

Christopher Pal
Christopher Pal
Distinguished Scientist

Distinguished Scientist at Low Data Learning located at Montreal, QC, Canada.