<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-02553655</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-20T02:36:04+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Building a syntactically annotated historical corpus of Basque</title>
            <title xml:lang="eu">Sintaktikoki etiketatutako euskarazko corpus historikoa eraikitzen</title>
            <author role="aut">
              <persName>
                <forename type="first">Ainara</forename>
                <surname>Estarrona</surname>
              </persName>
              <idno type="halauthorid">1830796-0</idno>
              <affiliation ref="#struct-302177"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Izaskun</forename>
                <surname>Etxeberria</surname>
              </persName>
              <idno type="halauthorid">1830797-0</idno>
              <affiliation ref="#struct-302177"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ricardo</forename>
                <forename type="middle">Rikardo, R.</forename>
                <surname>Etxepare</surname>
              </persName>
              <email type="md5">514363f54a0c739f38ce20177238b272</email>
              <email type="domain">iker.cnrs.fr</email>
              <idno type="idhal" notation="string">ricardo-etxepare</idno>
              <idno type="idhal" notation="numeric">183550</idno>
              <idno type="halauthorid" notation="string">47123-183550</idno>
              <idno type="IDREF">https://www.idref.fr/165566213</idno>
              <idno type="VIAF">https://viaf.org/viaf/288570553</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=SqFArqQAAAAJ</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1948-8248</idno>
              <affiliation ref="#struct-2561"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Manuel</forename>
                <surname>Padilla Moyano</surname>
              </persName>
              <email type="md5">2314685cd3dada751a960c13df2bd0d9</email>
              <email type="domain">yahoo.com</email>
              <idno type="idhal" notation="string">manuel-padilla</idno>
              <idno type="idhal" notation="numeric">183714</idno>
              <idno type="halauthorid" notation="string">40456-183714</idno>
              <idno type="IDREF">https://www.idref.fr/200812203</idno>
              <affiliation ref="#struct-2561"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ander</forename>
                <surname>Soraluze</surname>
              </persName>
              <idno type="halauthorid">1831876-0</idno>
              <affiliation ref="#struct-302177"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Admin</forename>
                <surname>HAL-UPPA</surname>
              </persName>
              <email type="md5">43b124e5dfa56f6a991394da698e5353</email>
              <email type="domain">univ-pau.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-12-03 11:26:36</date>
              <date type="whenModified">2026-03-30 17:34:00</date>
              <date type="whenReleased">2025-12-03 11:29:53</date>
              <date type="whenProduced">2020</date>
              <date type="whenEndEmbargoed">2025-12-03</date>
              <ref type="file" target="https://univ-pau.hal.science/hal-02553655v1/document">
                <date notBefore="2025-12-03"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://univ-pau.hal.science/hal-02553655v1/file/fontes50urte.15.pdf" id="file-5395169-4617540">
                <date notBefore="2025-12-03"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="951119">
                <persName>
                  <forename>Admin</forename>
                  <surname>HAL-UPPA</surname>
                </persName>
                <email type="md5">43b124e5dfa56f6a991394da698e5353</email>
                <email type="domain">univ-pau.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02553655</idno>
            <idno type="halUri">https://univ-pau.hal.science/hal-02553655</idno>
            <idno type="halBibtex">estarrona:hal-02553655</idno>
            <idno type="halRefHtml">Ekaitz Santazilia; Dorota Krajewska; Eneko Zuloaga; Borja Ariztimuño. &lt;i&gt;Fontes Linguae Vasconum 50 urte: Ekarpen berriak euskararen ikerketari = Nuevas aportaciones al estudio de la lengua vasca&lt;/i&gt;, Gobierno de Navarra, pp.237-251, 2020, 978-84-235-3561-3. &lt;a target="_blank" href="https://dx.doi.org/10.35462/fontes50urte.15"&gt;&amp;#x27E8;10.35462/fontes50urte.15&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Ekaitz Santazilia; Dorota Krajewska; Eneko Zuloaga; Borja Ariztimuño. Fontes Linguae Vasconum 50 urte: Ekarpen berriak euskararen ikerketari = Nuevas aportaciones al estudio de la lengua vasca, Gobierno de Navarra, pp.237-251, 2020, 978-84-235-3561-3. &amp;#x27E8;10.35462/fontes50urte.15&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://hal.science/licences/copyright/">Copyright - All rights reserved<ref corresp="#file-5395169-4617540"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SHS">Sciences de l'Homme et de la Société</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-PAU">Université de Pau et des Pays de l'Adour - E2S UPPA</idno>
            <idno type="stamp" n="AO-LINGUISTIQUE">Archives ouvertes de la Linguistique</idno>
            <idno type="stamp" n="IKER">IKER-Centre de recherche sur la langue et les textes basques</idno>
            <idno type="stamp" n="UNIV-BORDEAUX-MONTAIGNE">Université Bordeaux Montaigne</idno>
            <idno type="stamp" n="IKER_UMR5478">UMR 5478 IKER - Centre de recherche sur la langue et les textes basques </idno>
            <idno type="stamp" n="OR-COLLCODE">Portail Artxiker</idno>
            <idno type="stamp" n="ARTXIKER">Portail Artxiker</idno>
            <idno type="stamp" n="UPPA-OA" corresp="UNIV-PAU">uppa-oa</idno>
            <idno type="stamp" n="UPPA-2EI" corresp="UNIV-PAU">UPPA-Collège-2EI</idno>
            <idno type="stamp" n="UPPA-COLLEGES">UPPA STEE EI SSH</idno>
            <idno type="stamp" n="CNRS-SECTION-36">CNRS Sciences humaines &amp; sociales – section 36 : Sciences du langage</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Building a syntactically annotated historical corpus of Basque</title>
                <title xml:lang="eu">Sintaktikoki etiketatutako euskarazko corpus historikoa eraikitzen</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Ainara</forename>
                    <surname>Estarrona</surname>
                  </persName>
                  <idno type="halauthorid">1830796-0</idno>
                  <affiliation ref="#struct-302177"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Izaskun</forename>
                    <surname>Etxeberria</surname>
                  </persName>
                  <idno type="halauthorid">1830797-0</idno>
                  <affiliation ref="#struct-302177"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ricardo</forename>
                    <forename type="middle">Rikardo, R.</forename>
                    <surname>Etxepare</surname>
                  </persName>
                  <email type="md5">514363f54a0c739f38ce20177238b272</email>
                  <email type="domain">iker.cnrs.fr</email>
                  <idno type="idhal" notation="string">ricardo-etxepare</idno>
                  <idno type="idhal" notation="numeric">183550</idno>
                  <idno type="halauthorid" notation="string">47123-183550</idno>
                  <idno type="IDREF">https://www.idref.fr/165566213</idno>
                  <idno type="VIAF">https://viaf.org/viaf/288570553</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=SqFArqQAAAAJ</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1948-8248</idno>
                  <affiliation ref="#struct-2561"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Manuel</forename>
                    <surname>Padilla Moyano</surname>
                  </persName>
                  <email type="md5">2314685cd3dada751a960c13df2bd0d9</email>
                  <email type="domain">yahoo.com</email>
                  <idno type="idhal" notation="string">manuel-padilla</idno>
                  <idno type="idhal" notation="numeric">183714</idno>
                  <idno type="halauthorid" notation="string">40456-183714</idno>
                  <idno type="IDREF">https://www.idref.fr/200812203</idno>
                  <affiliation ref="#struct-2561"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ander</forename>
                    <surname>Soraluze</surname>
                  </persName>
                  <idno type="halauthorid">1831876-0</idno>
                  <affiliation ref="#struct-302177"/>
                </author>
              </analytic>
              <monogr>
                <idno type="isbn">978-84-235-3561-3</idno>
                <title level="m">Fontes Linguae Vasconum 50 urte: Ekarpen berriak euskararen ikerketari = Nuevas aportaciones al estudio de la lengua vasca</title>
                <editor>Ekaitz Santazilia</editor>
                <editor>Dorota Krajewska</editor>
                <editor>Eneko Zuloaga</editor>
                <editor>Borja Ariztimuño</editor>
                <imprint>
                  <publisher>Gobierno de Navarra</publisher>
                  <pubPlace>Iruña</pubPlace>
                  <biblScope unit="pp">237-251</biblScope>
                  <date type="datePub">2020</date>
                </imprint>
              </monogr>
              <idno type="doi">10.35462/fontes50urte.15</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="eu">Basque</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Digital Humanities</term>
                <term xml:lang="en">historical corpus</term>
                <term xml:lang="en">Natural Language Processing ( nlp)</term>
                <term xml:lang="en">diachronic syntax</term>
                <term xml:lang="eu">sintaxi diakronikoa</term>
                <term xml:lang="eu">Humanitate Digitalak</term>
                <term xml:lang="eu">corpus historikoa</term>
                <term xml:lang="eu">Hizkuntzaren Prozesamendua (hp)</term>
              </keywords>
              <classCode scheme="halDomain" n="shs.langue">Humanities and Social Sciences/Linguistics</classCode>
              <classCode scheme="halTypology" n="COUV">Book sections</classCode>
              <classCode scheme="halOldTypology" n="COUV">Book sections</classCode>
              <classCode scheme="halTreeTypology" n="COUV">Book sections</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>In this paper we present an ongoing project to build a morphosyntactically annotated historical corpus of Basque. The corpus will have around one million words, encompassing the most significant written production of Basque between the 15th and 18th centuries. Morphosyntactic tagging will allow for systematic searches at different levels of complexity: lemma, form, part of speech, morphosyntactic feature, and also a number of syntactic constructions. In addition, a set of metadata will enable searches based on socio-historical criteria too. Beyond being the first annotated historical corpus of Basque, through this project tools for language processing will be improved byanalysing Basque historical varieties more or less distant from present-day standard Basque. Moreover, this project aims to establish a model for further works in historicalcorpora of Basque.</p>
            </abstract>
            <abstract xml:lang="eu">
              <p>Lan honetan morfologikoki eta sintaktikoki etiketatutako euskararen corpus historikoaren proiektua aurkezten dugu. Corpusak xv - xviii . mende bitarteko euskalki guztietako ekoizpen idatzi esanguratsuena besarkatuko du, haren tamaina milioi bat hitz ingurukoa izanik. Etiketatze morfosintaktikoak hainbat konplexutasun-mailatako bilaketa sistematikoak ahalbidetuko ditu: lemaren, formaren, kategoria gramatikalaren, tasun morfosintaktikoaren, bai eta zenbait egitura sintaktikoren arabera ere. Halaber, corpusa metadatu-sorta batekin hornituko da, irizpide sozio-historikoen araberako bilaketak ere posible egiteko. Euskararen lehen corpus historiko anotatua sortzeaz gainera, proiektu honi esker hizkuntzaren prozesamenduko tresnak gaur egungo euskara batutik urruntzen diren barietateekin trebatuko dira. Harago, proiektu honek etorkizuneko euskara historikoaren corpusgintzarako oinarriak finkatu nahi lituzke.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-302177" status="VALID">
          <idno type="IdRef">027216152</idno>
          <idno type="ISNI">0000000121671098</idno>
          <idno type="ROR">https://ror.org/000xsnr85</idno>
          <idno type="Wikidata">Q1232428</idno>
          <orgName>Universidad del País Vasco [Espainia] / Euskal Herriko Unibertsitatea [España] = University of the Basque Country [Spain] = Université du pays basque [Espagne]</orgName>
          <orgName type="acronym">UPV / EHU</orgName>
          <date type="start">1980-02-25</date>
          <desc>
            <address>
              <addrLine>Barrio Sarriena s/n, 48940 Leioa, BizkaiaCampus d'Álava : Vice-Rectorado, San Antonio 41, 01005 Vitoria ; campus de Biscaye et services centraux : Apdo 1397, 48080 Bilbao ; campus de Guipúzcoa : Vice-Rectorado, Fuenterrabia 13-1° , 20006 San Sebastián</addrLine>
              <country key="ES"/>
            </address>
            <ref type="url">http://www.ehu.eus/es/home</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-2561" status="VALID">
          <idno type="IdRef">035167602</idno>
          <idno type="ISNI">0000000119395549</idno>
          <idno type="RNSR">199911943R</idno>
          <idno type="ROR">https://ror.org/03bj0v820</idno>
          <idno type="Wikidata">Q2945450</idno>
          <orgName>Centre de recherche sur la langue et les textes basques</orgName>
          <orgName type="acronym">IKER</orgName>
          <date type="start">1999-01-01</date>
          <desc>
            <address>
              <addrLine>IKER (UMR 5478) - Château-Neuf; Place Paul Bert, 64100 BAYONNE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.iker.cnrs.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301085" type="direct"/>
            <relation active="#struct-412629" type="direct"/>
            <relation name="UMR5478" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301085" status="VALID">
          <idno type="IdRef">026403668</idno>
          <idno type="ISNI">000000012289818X</idno>
          <idno type="ROR">https://ror.org/01frn9647</idno>
          <idno type="Wikidata">Q572968</idno>
          <orgName>Université de Pau et des Pays de l'Adour</orgName>
          <orgName type="acronym">UPPA</orgName>
          <date type="start">1970-12-17</date>
          <desc>
            <address>
              <addrLine>Avenue de l'Université - BP 576 - 64012 Pau Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-pau.fr/fr/index.html</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-412629" status="VALID">
          <idno type="IdRef">027548392</idno>
          <idno type="ROR">https://ror.org/03pbgwk21</idno>
          <orgName>Université Bordeaux Montaigne</orgName>
          <orgName type="acronym">UBM</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-bordeaux-montaigne.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>