<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-03-09T05:48:23Z</responseDate>
  <request identifier="oai:repository.ninjal.ac.jp:00003617" metadataPrefix="jpcoar_1.0" verb="GetRecord">https://repository.ninjal.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:repository.ninjal.ac.jp:00003617</identifier>
        <datestamp>2023-05-15T14:47:46Z</datestamp>
        <setSpec>320:324</setSpec>
        <setSpec>320:377</setSpec>
      </header>
      <metadata>
        <jpcoar:jpcoar xmlns:datacite="https://schema.datacite.org/meta/kernel-4/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcndl="http://ndl.go.jp/dcndl/terms/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:jpcoar="https://github.com/JPCOAR/schema/blob/master/1.0/" xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:rioxxterms="http://www.rioxx.net/schema/v2.0/rioxxterms/" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="https://github.com/JPCOAR/schema/blob/master/1.0/" xsi:schemaLocation="https://github.com/JPCOAR/schema/blob/master/1.0/jpcoar_scm.xsd">
          <dc:title xml:lang="en">CHJ-WLSP : Annotation of 'Word List by Semantic Principles' Labels for the Corpus of Historical Japanese</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Asahara, Masayuki</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Ikegami, Nao</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Suzuki, Tai</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Ichimura, Taro</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Kondo, Asuko</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Kato, Sachi</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Yamazaki, Makoto</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:subject xml:lang="en" subjectScheme="Other">Historical Japanese</jpcoar:subject>
          <jpcoar:subject xml:lang="en" subjectScheme="Other">Word Sense Annotation</jpcoar:subject>
          <datacite:description descriptionType="Other">application/pdf</datacite:description>
          <datacite:description descriptionType="Other">National Institute for Japanese Language and Linguistics / Tokyo University of Foreign Studies</datacite:description>
          <datacite:description descriptionType="Other">Saitama University</datacite:description>
          <datacite:description descriptionType="Other">University of Tokyo</datacite:description>
          <datacite:description descriptionType="Other">Kyoto Prefectural University</datacite:description>
          <datacite:description descriptionType="Other">University of Tokyo</datacite:description>
          <datacite:description descriptionType="Other">Mejiro University</datacite:description>
          <datacite:description descriptionType="Other">National Institute for Japanese Language and Linguistics</datacite:description>
          <datacite:description descriptionType="Other">This article presents a word-sense annotation for the Corpus of Historical Japanese: a mashed-up Japanese lexicon based on the 'Word List by Semantic Principles' (WLSP). The WLSP is a large-scale Japanese thesaurus that includes 98,241 entries with syntactic and hierarchical semantic categories. The historical WLSP is also compiled for the words in ancient Japanese. We utilized a morpheme-word sense alignment table to extract all possible word sense candidates for each word appearing in the target corpus. Then, we manually disambiguated the word senses for 647,751 words in the texts from the 10th century to 1910.</datacite:description>
          <dc:publisher>European Language Resources Association</dc:publisher>
          <datacite:date dateType="Issued">2022</datacite:date>
          <dc:language>eng</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_5794">conference paper</dc:type>
          <oaire:version rdf:resource="http://purl.org/coar/version/c_970fb48d4fbd8a85">VoR</oaire:version>
          <jpcoar:identifier identifierType="URI">https://repository.ninjal.ac.jp/records/3617</jpcoar:identifier>
          <jpcoar:sourceTitle xml:lang="en">Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages(LT4HALA 2022)</jpcoar:sourceTitle>
          <jpcoar:pageStart>31</jpcoar:pageStart>
          <jpcoar:pageEnd>37</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI label="lt4hala2022_31.pdf">https://repository.ninjal.ac.jp/record/3617/files/lt4hala2022_31.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>545.6 kB</jpcoar:extent>
            <datacite:date dateType="Available">2022-08-17</datacite:date>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
