@inproceedings{sileo-etal-2024-generating,
title = "Generating Multiple-choice Questions for Medical Question Answering with Distractors and Cue-masking",
author = "Sileo, Damien and
Uma, Kanimozhi and
Moens, Marie-Francine",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.675/",
pages = "7647--7653",
abstract = "Medical multiple-choice question answering (MCQA) is a challenging evaluation for medical natural language processing and a helpful task in itself. Medical questions may describe patient symptoms and ask for the correct diagnosis, which requires domain knowledge and complex reasoning. Standard language modeling pretraining alone is not sufficient to achieve the best results with BERT-base size (Devlin et al., 2019) encoders. Jin et al. (2020) showed that focusing masked language modeling on disease name prediction when using medical encyclopedic paragraphs as input leads to considerable MCQA accuracy improvement. In this work, we show that (1) fine-tuning on generated MCQA dataset outperforms the masked language modeling based objective and (2) correctly masking the cues to the answers is critical for good performance. We release new pretraining datasets and achieve state-of-the-art results on 4 MCQA datasets, notably +5.7{\%} with base-size model on MedQA-USMLE."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sileo-etal-2024-generating">
<titleInfo>
<title>Generating Multiple-choice Questions for Medical Question Answering with Distractors and Cue-masking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Sileo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanimozhi</namePart>
<namePart type="family">Uma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical multiple-choice question answering (MCQA) is a challenging evaluation for medical natural language processing and a helpful task in itself. Medical questions may describe patient symptoms and ask for the correct diagnosis, which requires domain knowledge and complex reasoning. Standard language modeling pretraining alone is not sufficient to achieve the best results with BERT-base size (Devlin et al., 2019) encoders. Jin et al. (2020) showed that focusing masked language modeling on disease name prediction when using medical encyclopedic paragraphs as input leads to considerable MCQA accuracy improvement. In this work, we show that (1) fine-tuning on generated MCQA dataset outperforms the masked language modeling based objective and (2) correctly masking the cues to the answers is critical for good performance. We release new pretraining datasets and achieve state-of-the-art results on 4 MCQA datasets, notably +5.7% with base-size model on MedQA-USMLE.</abstract>
<identifier type="citekey">sileo-etal-2024-generating</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.675/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7647</start>
<end>7653</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Multiple-choice Questions for Medical Question Answering with Distractors and Cue-masking
%A Sileo, Damien
%A Uma, Kanimozhi
%A Moens, Marie-Francine
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F sileo-etal-2024-generating
%X Medical multiple-choice question answering (MCQA) is a challenging evaluation for medical natural language processing and a helpful task in itself. Medical questions may describe patient symptoms and ask for the correct diagnosis, which requires domain knowledge and complex reasoning. Standard language modeling pretraining alone is not sufficient to achieve the best results with BERT-base size (Devlin et al., 2019) encoders. Jin et al. (2020) showed that focusing masked language modeling on disease name prediction when using medical encyclopedic paragraphs as input leads to considerable MCQA accuracy improvement. In this work, we show that (1) fine-tuning on generated MCQA dataset outperforms the masked language modeling based objective and (2) correctly masking the cues to the answers is critical for good performance. We release new pretraining datasets and achieve state-of-the-art results on 4 MCQA datasets, notably +5.7% with base-size model on MedQA-USMLE.
%U https://aclanthology.org/2024.lrec-main.675/
%P 7647-7653
Markdown (Informal)
[Generating Multiple-choice Questions for Medical Question Answering with Distractors and Cue-masking](https://aclanthology.org/2024.lrec-main.675/) (Sileo et al., LREC-COLING 2024)
ACL