@inproceedings{labrak-etal-2022-frenchmedmcqa,
title = "{F}rench{M}ed{MCQA}: A {F}rench Multiple-Choice Question Answering Dataset for Medical domain",
author = "Labrak, Yanis and
Bazoge, Adrien and
Dufour, Richard and
Daille, Beatrice and
Gourraud, Pierre-Antoine and
Morin, Emmanuel and
Rouvier, Mickael",
editor = "Lavelli, Alberto and
Holderness, Eben and
Jimeno Yepes, Antonio and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.louhi-1.5",
doi = "10.18653/v1/2022.louhi-1.5",
pages = "41--46",
abstract = "This paper introduces FrenchMedMCQA, the first publicly available Multiple-Choice Question Answering (MCQA) dataset in French for medical domain. It is composed of 3,105 questions taken from real exams of the French medical specialization diploma in pharmacy, mixing single and multiple answers. Each instance of the dataset contains an identifier, a question, five possible answers and their manual correction(s). We also propose first baseline models to automatically process this MCQA task in order to report on the current performances and to highlight the difficulty of the task. A detailed analysis of the results showed that it is necessary to have representations adapted to the medical domain or to the MCQA task: in our case, English specialized models yielded better results than generic French ones, even though FrenchMedMCQA is in French. Corpus, models and tools are available online.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="labrak-etal-2022-frenchmedmcqa">
<titleInfo>
<title>FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanis</namePart>
<namePart type="family">Labrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrien</namePart>
<namePart type="family">Bazoge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Dufour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Daille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre-Antoine</namePart>
<namePart type="family">Gourraud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Morin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mickael</namePart>
<namePart type="family">Rouvier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces FrenchMedMCQA, the first publicly available Multiple-Choice Question Answering (MCQA) dataset in French for medical domain. It is composed of 3,105 questions taken from real exams of the French medical specialization diploma in pharmacy, mixing single and multiple answers. Each instance of the dataset contains an identifier, a question, five possible answers and their manual correction(s). We also propose first baseline models to automatically process this MCQA task in order to report on the current performances and to highlight the difficulty of the task. A detailed analysis of the results showed that it is necessary to have representations adapted to the medical domain or to the MCQA task: in our case, English specialized models yielded better results than generic French ones, even though FrenchMedMCQA is in French. Corpus, models and tools are available online.</abstract>
<identifier type="citekey">labrak-etal-2022-frenchmedmcqa</identifier>
<identifier type="doi">10.18653/v1/2022.louhi-1.5</identifier>
<location>
<url>https://aclanthology.org/2022.louhi-1.5</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>41</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain
%A Labrak, Yanis
%A Bazoge, Adrien
%A Dufour, Richard
%A Daille, Beatrice
%A Gourraud, Pierre-Antoine
%A Morin, Emmanuel
%A Rouvier, Mickael
%Y Lavelli, Alberto
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F labrak-etal-2022-frenchmedmcqa
%X This paper introduces FrenchMedMCQA, the first publicly available Multiple-Choice Question Answering (MCQA) dataset in French for medical domain. It is composed of 3,105 questions taken from real exams of the French medical specialization diploma in pharmacy, mixing single and multiple answers. Each instance of the dataset contains an identifier, a question, five possible answers and their manual correction(s). We also propose first baseline models to automatically process this MCQA task in order to report on the current performances and to highlight the difficulty of the task. A detailed analysis of the results showed that it is necessary to have representations adapted to the medical domain or to the MCQA task: in our case, English specialized models yielded better results than generic French ones, even though FrenchMedMCQA is in French. Corpus, models and tools are available online.
%R 10.18653/v1/2022.louhi-1.5
%U https://aclanthology.org/2022.louhi-1.5
%U https://doi.org/10.18653/v1/2022.louhi-1.5
%P 41-46
Markdown (Informal)
[FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain](https://aclanthology.org/2022.louhi-1.5) (Labrak et al., Louhi 2022)
ACL