@inproceedings{tashiro-etal-2026-mednormj,
title = "{M}ed{N}orm{J}: A Benchmark Dataset for Medical Concept Normalization in {J}apanese Clinical Documents",
author = "Tashiro, Yuki and
Shimizu, Seiji and
Nishiyama, Tomohiro and
Wakamiya, Shoko and
Aramaki, Eiji",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical {NLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.clinicalnlp-1.36/",
doi = "10.63317/3tc32wmofkbm",
pages = "324--335",
abstract = "Medical concept normalization in clinical text is a fundamental technology for the secondary use of clinical data. However, constructing annotated resources for this task is challenging because annotation is both expertise-intensive and methodologically complex. As a result, a standard evaluation dataset for Japanese has yet to be established. In this study, we introduce a Japanese dataset for medical concept normalization, MedNormJ, which will be publicly available. The dataset consists of 397 pairs of medical expressions and their corresponding normalized disease names, manually curated from 96 medical documents, including case reports and radiology reports. Furthermore, we conduct comparative experiments using existing normalization approaches to benchmark their performance on this dataset in terms of both accuracy and computational efficiency. Through these experiments, we clarify the present performance level and identify remaining challenges specific to Japanese medical concept normalization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tashiro-etal-2026-mednormj">
<titleInfo>
<title>MedNormJ: A Benchmark Dataset for Medical Concept Normalization in Japanese Clinical Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Tashiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Tomohiro</namePart>
<namePart type="family">Nishiyama</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>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
</titleInfo>
<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">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical concept normalization in clinical text is a fundamental technology for the secondary use of clinical data. However, constructing annotated resources for this task is challenging because annotation is both expertise-intensive and methodologically complex. As a result, a standard evaluation dataset for Japanese has yet to be established. In this study, we introduce a Japanese dataset for medical concept normalization, MedNormJ, which will be publicly available. The dataset consists of 397 pairs of medical expressions and their corresponding normalized disease names, manually curated from 96 medical documents, including case reports and radiology reports. Furthermore, we conduct comparative experiments using existing normalization approaches to benchmark their performance on this dataset in terms of both accuracy and computational efficiency. Through these experiments, we clarify the present performance level and identify remaining challenges specific to Japanese medical concept normalization.</abstract>
<identifier type="citekey">tashiro-etal-2026-mednormj</identifier>
<identifier type="doi">10.63317/3tc32wmofkbm</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.36/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>324</start>
<end>335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedNormJ: A Benchmark Dataset for Medical Concept Normalization in Japanese Clinical Documents
%A Tashiro, Yuki
%A Shimizu, Seiji
%A Nishiyama, Tomohiro
%A Wakamiya, Shoko
%A Aramaki, Eiji
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F tashiro-etal-2026-mednormj
%X Medical concept normalization in clinical text is a fundamental technology for the secondary use of clinical data. However, constructing annotated resources for this task is challenging because annotation is both expertise-intensive and methodologically complex. As a result, a standard evaluation dataset for Japanese has yet to be established. In this study, we introduce a Japanese dataset for medical concept normalization, MedNormJ, which will be publicly available. The dataset consists of 397 pairs of medical expressions and their corresponding normalized disease names, manually curated from 96 medical documents, including case reports and radiology reports. Furthermore, we conduct comparative experiments using existing normalization approaches to benchmark their performance on this dataset in terms of both accuracy and computational efficiency. Through these experiments, we clarify the present performance level and identify remaining challenges specific to Japanese medical concept normalization.
%R 10.63317/3tc32wmofkbm
%U https://aclanthology.org/2026.clinicalnlp-1.36/
%U https://doi.org/10.63317/3tc32wmofkbm
%P 324-335
Markdown (Informal)
[MedNormJ: A Benchmark Dataset for Medical Concept Normalization in Japanese Clinical Documents](https://aclanthology.org/2026.clinicalnlp-1.36/) (Tashiro et al., ClinicalNLP 2026)
ACL