@inproceedings{horiguchi-etal-2026-jmedwic,
title = "{JM}ed{W}i{C}: A {J}apanese Word-in-Context Dataset in the Medical Domain",
author = "Horiguchi, Koki and
Sugiyama, Seiji and
Kajiwara, Tomoyuki 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-1.24/",
doi = "10.63317/2wqoixeze6fo",
pages = "222--227",
abstract = "We release JMedWiC, a Japanese dataset for Word-in-Context (WiC) tasks specifically tailored to the medical domain. To address the challenge of word sense disambiguation, where the meaning of a word varies depending on its context, previous research has developed WiC datasets to evaluate word sense identity by determining whether a target word shares the same sense across two given contexts. In the medical domain, the misinterpretation of word senses can hinder the accurate comprehension of medical information; however, there is currently no Japanese WiC dataset specialized for this domain. Moreover, existing WiC datasets have been constructed using lexical resources with sense inventories, such as WordNet and UMLS, but such resources are not sufficiently developed for Japanese. Therefore, we construct a Japanese WiC dataset in the medical domain by manually annotating sense-identity labels for target words in context pairs automatically extracted from a large-scale corpus, without relying on lexical resources."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="horiguchi-etal-2026-jmedwic">
<titleInfo>
<title>JMedWiC: A Japanese Word-in-Context Dataset in the Medical Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Koki</namePart>
<namePart type="family">Horiguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seiji</namePart>
<namePart type="family">Sugiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</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>We release JMedWiC, a Japanese dataset for Word-in-Context (WiC) tasks specifically tailored to the medical domain. To address the challenge of word sense disambiguation, where the meaning of a word varies depending on its context, previous research has developed WiC datasets to evaluate word sense identity by determining whether a target word shares the same sense across two given contexts. In the medical domain, the misinterpretation of word senses can hinder the accurate comprehension of medical information; however, there is currently no Japanese WiC dataset specialized for this domain. Moreover, existing WiC datasets have been constructed using lexical resources with sense inventories, such as WordNet and UMLS, but such resources are not sufficiently developed for Japanese. Therefore, we construct a Japanese WiC dataset in the medical domain by manually annotating sense-identity labels for target words in context pairs automatically extracted from a large-scale corpus, without relying on lexical resources.</abstract>
<identifier type="citekey">horiguchi-etal-2026-jmedwic</identifier>
<identifier type="doi">10.63317/2wqoixeze6fo</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.24/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>222</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JMedWiC: A Japanese Word-in-Context Dataset in the Medical Domain
%A Horiguchi, Koki
%A Sugiyama, Seiji
%A Kajiwara, Tomoyuki
%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 horiguchi-etal-2026-jmedwic
%X We release JMedWiC, a Japanese dataset for Word-in-Context (WiC) tasks specifically tailored to the medical domain. To address the challenge of word sense disambiguation, where the meaning of a word varies depending on its context, previous research has developed WiC datasets to evaluate word sense identity by determining whether a target word shares the same sense across two given contexts. In the medical domain, the misinterpretation of word senses can hinder the accurate comprehension of medical information; however, there is currently no Japanese WiC dataset specialized for this domain. Moreover, existing WiC datasets have been constructed using lexical resources with sense inventories, such as WordNet and UMLS, but such resources are not sufficiently developed for Japanese. Therefore, we construct a Japanese WiC dataset in the medical domain by manually annotating sense-identity labels for target words in context pairs automatically extracted from a large-scale corpus, without relying on lexical resources.
%R 10.63317/2wqoixeze6fo
%U https://aclanthology.org/2026.clinicalnlp-1.24/
%U https://doi.org/10.63317/2wqoixeze6fo
%P 222-227
Markdown (Informal)
[JMedWiC: A Japanese Word-in-Context Dataset in the Medical Domain](https://aclanthology.org/2026.clinicalnlp-1.24/) (Horiguchi et al., ClinicalNLP 2026)
ACL
- Koki Horiguchi, Seiji Sugiyama, Tomoyuki Kajiwara, Shoko Wakamiya, and Eiji Aramaki. 2026. JMedWiC: A Japanese Word-in-Context Dataset in the Medical Domain. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 222–227, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).