@inproceedings{kim-etal-2024-ku,
title = "{KU}-{DMIS} at {EHRSQL} 2024 : Generating {SQL} query via question templatization in {EHR}",
author = "Kim, Hajung and
Kim, Chanhwi and
Lee, Hoonick and
Jang, Kyochul and
Lee, Jiwoo and
Lee, Kyungjae and
Kim, Gangwoo and
Kang, Jaewoo",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.64",
doi = "10.18653/v1/2024.clinicalnlp-1.64",
pages = "672--686",
abstract = "Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request information outside the database{'}s scope or exceed the system{'}s capabilities. In this paper, we introduce a novel text-to-SQL framework that focuses on standardizing the structure of questions into a templated format. Our framework begins by fine-tuning GPT-3.5-turbo, a powerful large language model (LLM), with detailed prompts involving the table schemas of the EHR database system. Our approach shows promising results on the EHRSQL-2024 benchmark dataset, part of the ClinicalNLP shared task. Although fine-tuning GPT achieves third place on the development set, it struggled with the diverse questions in the test set. With our framework, we improve our system{'}s adaptability and achieve fourth position in the official leaderboard of the EHRSQL-2024 challenge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-ku">
<titleInfo>
<title>KU-DMIS at EHRSQL 2024 : Generating SQL query via question templatization in EHR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hajung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanhwi</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoonick</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyochul</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiwoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyungjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gangwoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaewoo</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request information outside the database’s scope or exceed the system’s capabilities. In this paper, we introduce a novel text-to-SQL framework that focuses on standardizing the structure of questions into a templated format. Our framework begins by fine-tuning GPT-3.5-turbo, a powerful large language model (LLM), with detailed prompts involving the table schemas of the EHR database system. Our approach shows promising results on the EHRSQL-2024 benchmark dataset, part of the ClinicalNLP shared task. Although fine-tuning GPT achieves third place on the development set, it struggled with the diverse questions in the test set. With our framework, we improve our system’s adaptability and achieve fourth position in the official leaderboard of the EHRSQL-2024 challenge.</abstract>
<identifier type="citekey">kim-etal-2024-ku</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.64</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.64</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>672</start>
<end>686</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KU-DMIS at EHRSQL 2024 : Generating SQL query via question templatization in EHR
%A Kim, Hajung
%A Kim, Chanhwi
%A Lee, Hoonick
%A Jang, Kyochul
%A Lee, Jiwoo
%A Lee, Kyungjae
%A Kim, Gangwoo
%A Kang, Jaewoo
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F kim-etal-2024-ku
%X Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request information outside the database’s scope or exceed the system’s capabilities. In this paper, we introduce a novel text-to-SQL framework that focuses on standardizing the structure of questions into a templated format. Our framework begins by fine-tuning GPT-3.5-turbo, a powerful large language model (LLM), with detailed prompts involving the table schemas of the EHR database system. Our approach shows promising results on the EHRSQL-2024 benchmark dataset, part of the ClinicalNLP shared task. Although fine-tuning GPT achieves third place on the development set, it struggled with the diverse questions in the test set. With our framework, we improve our system’s adaptability and achieve fourth position in the official leaderboard of the EHRSQL-2024 challenge.
%R 10.18653/v1/2024.clinicalnlp-1.64
%U https://aclanthology.org/2024.clinicalnlp-1.64
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.64
%P 672-686
Markdown (Informal)
[KU-DMIS at EHRSQL 2024 : Generating SQL query via question templatization in EHR](https://aclanthology.org/2024.clinicalnlp-1.64) (Kim et al., ClinicalNLP-WS 2024)
ACL
- Hajung Kim, Chanhwi Kim, Hoonick Lee, Kyochul Jang, Jiwoo Lee, Kyungjae Lee, Gangwoo Kim, and Jaewoo Kang. 2024. KU-DMIS at EHRSQL 2024 : Generating SQL query via question templatization in EHR. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 672–686, Mexico City, Mexico. Association for Computational Linguistics.