@inproceedings{somov-etal-2024-airi,
title = "{AIRI} {NLP} Team at {EHRSQL} 2024 Shared Task: T5 and Logistic Regression to the Rescue",
author = "Somov, Oleg and
Dontsov, Alexey and
Tutubalina, Elena",
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-1.43",
doi = "10.18653/v1/2024.clinicalnlp-1.43",
pages = "431--438",
abstract = "This paper presents a system developed for the Clinical NLP 2024 Shared Task, focusing on reliable text-to-SQL modeling on Electronic Health Records (EHRs). The goal is to create a model that accurately generates SQL queries for answerable questions while avoiding incorrect responses and handling unanswerable queries. Our approach comprises three main components: a query correspondence model, a text-to-SQL model, and an SQL verifier.For the query correspondence model, we trained a logistic regression model using hand-crafted features to distinguish between answerable and unanswerable queries. As for the text-to-SQL model, we utilized T5-3B as a pretrained language model, further fine-tuned on pairs of natural language questions and corresponding SQL queries. Finally, we applied the SQL verifier to inspect the resulting SQL queries.During the evaluation stage of the shared task, our system achieved an accuracy of 68.9 {\%} (metric version without penalty), positioning it at the fifth-place ranking. While our approach did not surpass solutions based on large language models (LMMs) like ChatGPT, it demonstrates the promising potential of domain-specific specialized models that are more resource-efficient. The code is publicly available at https://github.com/runnerup96/EHRSQL-text2sql-solution.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="somov-etal-2024-airi">
<titleInfo>
<title>AIRI NLP Team at EHRSQL 2024 Shared Task: T5 and Logistic Regression to the Rescue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Somov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Dontsov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</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>This paper presents a system developed for the Clinical NLP 2024 Shared Task, focusing on reliable text-to-SQL modeling on Electronic Health Records (EHRs). The goal is to create a model that accurately generates SQL queries for answerable questions while avoiding incorrect responses and handling unanswerable queries. Our approach comprises three main components: a query correspondence model, a text-to-SQL model, and an SQL verifier.For the query correspondence model, we trained a logistic regression model using hand-crafted features to distinguish between answerable and unanswerable queries. As for the text-to-SQL model, we utilized T5-3B as a pretrained language model, further fine-tuned on pairs of natural language questions and corresponding SQL queries. Finally, we applied the SQL verifier to inspect the resulting SQL queries.During the evaluation stage of the shared task, our system achieved an accuracy of 68.9 % (metric version without penalty), positioning it at the fifth-place ranking. While our approach did not surpass solutions based on large language models (LMMs) like ChatGPT, it demonstrates the promising potential of domain-specific specialized models that are more resource-efficient. The code is publicly available at https://github.com/runnerup96/EHRSQL-text2sql-solution.</abstract>
<identifier type="citekey">somov-etal-2024-airi</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.43</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.43</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>431</start>
<end>438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AIRI NLP Team at EHRSQL 2024 Shared Task: T5 and Logistic Regression to the Rescue
%A Somov, Oleg
%A Dontsov, Alexey
%A Tutubalina, Elena
%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 somov-etal-2024-airi
%X This paper presents a system developed for the Clinical NLP 2024 Shared Task, focusing on reliable text-to-SQL modeling on Electronic Health Records (EHRs). The goal is to create a model that accurately generates SQL queries for answerable questions while avoiding incorrect responses and handling unanswerable queries. Our approach comprises three main components: a query correspondence model, a text-to-SQL model, and an SQL verifier.For the query correspondence model, we trained a logistic regression model using hand-crafted features to distinguish between answerable and unanswerable queries. As for the text-to-SQL model, we utilized T5-3B as a pretrained language model, further fine-tuned on pairs of natural language questions and corresponding SQL queries. Finally, we applied the SQL verifier to inspect the resulting SQL queries.During the evaluation stage of the shared task, our system achieved an accuracy of 68.9 % (metric version without penalty), positioning it at the fifth-place ranking. While our approach did not surpass solutions based on large language models (LMMs) like ChatGPT, it demonstrates the promising potential of domain-specific specialized models that are more resource-efficient. The code is publicly available at https://github.com/runnerup96/EHRSQL-text2sql-solution.
%R 10.18653/v1/2024.clinicalnlp-1.43
%U https://aclanthology.org/2024.clinicalnlp-1.43
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.43
%P 431-438
Markdown (Informal)
[AIRI NLP Team at EHRSQL 2024 Shared Task: T5 and Logistic Regression to the Rescue](https://aclanthology.org/2024.clinicalnlp-1.43) (Somov et al., ClinicalNLP-WS 2024)
ACL