EHR-SeqSQL : A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records

TL;DR

EHR-SeqSQL is a large, novel dataset for sequential, interactive text-to-SQL tasks in electronic health records, emphasizing compositionality, efficiency, and multi-turn question handling.

Contribution

The paper introduces EHR-SeqSQL, the first medical sequential text-to-SQL dataset with contextual questions and a focus on compositionality and efficiency.

Findings

Multi-turn approach outperforms single-turn in learning compositionality.

Dataset enhances SQL query efficiency with specially crafted tokens.

EHR-SeqSQL bridges practical medical data needs and research.

Abstract

In this paper, we introduce EHR-SeqSQL, a novel sequential text-to-SQL dataset for Electronic Health Record (EHR) databases. EHR-SeqSQL is designed to address critical yet underexplored aspects in text-to-SQL parsing: interactivity, compositionality, and efficiency. To the best of our knowledge, EHR-SeqSQL is not only the largest but also the first medical text-to-SQL dataset benchmark to include sequential and contextual questions. We provide a data split and the new test set designed to assess compositional generalization ability. Our experiments demonstrate the superiority of a multi-turn approach over a single-turn approach in learning compositionality. Additionally, our dataset integrates specially crafted tokens into SQL queries to improve execution efficiency. With EHR-SeqSQL, we aim to bridge the gap between practical needs and academic research in the text-to-SQL domain. EHR-SeqSQL is available at https://github.com/seonhee99/EHR-SeqSQL.