@inproceedings{shimizu-etal-2024-generating,
title = "Generating Distributable Surrogate Corpus for Medical Multi-label Classification",
author = "Shimizu, Seiji and
Yada, Shuntaro and
Wakamiya, Shoko and
Aramaki, Eiji",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Thompson, Paul and
Ondov, Brian",
booktitle = "Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.cl4health-1.19",
pages = "153--162",
abstract = "In medical and social media domains, annotated corpora are often hard to distribute due to copyrights and privacy issues. To overcome this situation, we propose a new method to generate a surrogate corpus for a downstream task by using a text generation model. We chose a medical multi-label classification task, MedWeb, in which patient-generated short messages express multiple symptoms. We first fine-tuned text generation models with different prompting designs on the original corpus to obtain synthetic versions of that corpus. To assess the viability of the generated corpora for the downstream task, we compared the performance of multi-label classification models trained either on the original or the surrogate corpora. The results and the error analysis showed the difficulty of generating surrogate corpus in multi-label settings, suggesting text generation under complex conditions is not trivial. On the other hand, our experiment demonstrates that the generated corpus with a sentinel-based prompting is comparatively viable in a single-label (multiclass) classification setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shimizu-etal-2024-generating">
<titleInfo>
<title>Generating Distributable Surrogate Corpus for Medical Multi-label Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seiji</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuntaro</namePart>
<namePart type="family">Yada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoko</namePart>
<namePart type="family">Wakamiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiji</namePart>
<namePart type="family">Aramaki</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 First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Ondov</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>In medical and social media domains, annotated corpora are often hard to distribute due to copyrights and privacy issues. To overcome this situation, we propose a new method to generate a surrogate corpus for a downstream task by using a text generation model. We chose a medical multi-label classification task, MedWeb, in which patient-generated short messages express multiple symptoms. We first fine-tuned text generation models with different prompting designs on the original corpus to obtain synthetic versions of that corpus. To assess the viability of the generated corpora for the downstream task, we compared the performance of multi-label classification models trained either on the original or the surrogate corpora. The results and the error analysis showed the difficulty of generating surrogate corpus in multi-label settings, suggesting text generation under complex conditions is not trivial. On the other hand, our experiment demonstrates that the generated corpus with a sentinel-based prompting is comparatively viable in a single-label (multiclass) classification setting.</abstract>
<identifier type="citekey">shimizu-etal-2024-generating</identifier>
<location>
<url>https://aclanthology.org/2024.cl4health-1.19</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>153</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Distributable Surrogate Corpus for Medical Multi-label Classification
%A Shimizu, Seiji
%A Yada, Shuntaro
%A Wakamiya, Shoko
%A Aramaki, Eiji
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Thompson, Paul
%Y Ondov, Brian
%S Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F shimizu-etal-2024-generating
%X In medical and social media domains, annotated corpora are often hard to distribute due to copyrights and privacy issues. To overcome this situation, we propose a new method to generate a surrogate corpus for a downstream task by using a text generation model. We chose a medical multi-label classification task, MedWeb, in which patient-generated short messages express multiple symptoms. We first fine-tuned text generation models with different prompting designs on the original corpus to obtain synthetic versions of that corpus. To assess the viability of the generated corpora for the downstream task, we compared the performance of multi-label classification models trained either on the original or the surrogate corpora. The results and the error analysis showed the difficulty of generating surrogate corpus in multi-label settings, suggesting text generation under complex conditions is not trivial. On the other hand, our experiment demonstrates that the generated corpus with a sentinel-based prompting is comparatively viable in a single-label (multiclass) classification setting.
%U https://aclanthology.org/2024.cl4health-1.19
%P 153-162
Markdown (Informal)
[Generating Distributable Surrogate Corpus for Medical Multi-label Classification](https://aclanthology.org/2024.cl4health-1.19) (Shimizu et al., CL4Health-WS 2024)
ACL