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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ryu, Jaehee, Cho, Seonhee, Lee, Gyubok, Choi, Edward
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929442294595584
author Ryu, Jaehee
Cho, Seonhee
Lee, Gyubok
Choi, Edward
author_facet Ryu, Jaehee
Cho, Seonhee
Lee, Gyubok
Choi, Edward
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00019
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EHR-SeqSQL : A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records
Ryu, Jaehee
Cho, Seonhee
Lee, Gyubok
Choi, Edward
Computation and Language
Artificial Intelligence
Databases
Information Retrieval
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.
title EHR-SeqSQL : A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records
topic Computation and Language
Artificial Intelligence
Databases
Information Retrieval
url https://arxiv.org/abs/2406.00019