Dataset Open Access

Catalan United Nations v1.0 test set

Marta R. Costa-jussà


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.3888414">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.3888414</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3888414"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-5703-520X">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-5703-520X</dct:identifier>
        <foaf:name>Marta R. Costa-jussà</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Universitat Politècnica de Catalunya</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Catalan United Nations v1.0 test set</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2020</dct:issued>
    <dcat:keyword>Multilingual Parallel Data</dcat:keyword>
    <dcat:keyword>Benchmark</dcat:keyword>
    <dcat:keyword>Catalan</dcat:keyword>
    <dcat:keyword>United Nations</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-06-10</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/CA"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3888414"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3888414</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="https://doi.org/10.1145/3312575"/>
    <dct:relation rdf:resource="https://www.aclweb.org/anthology/L16-1561"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3888413"/>
    <dct:description>&lt;p&gt;Catalan version [1] of the test set from the United Nations v1.0 [2]. The translation was performed in two steps: we did a first automatic translation from the Spanish test set version into Catalan and then a professional translator post-edited the output.&lt;/p&gt; &lt;p&gt;&lt;br&gt; [1] Marta R. Costa-Juss&amp;agrave;, No&amp;eacute; Casas, Carlos Escolano, and Jos&amp;eacute; A. R. Fonollosa. 2019. Chinese-Catalan: A Neural Machine Translation Approach Based on Pivoting and Attention Mechanisms. &lt;em&gt;ACM Trans. Asian Low-Resour. Lang. Inf. Process.&lt;/em&gt; 18, 4, Article 43 (August 2019), 8 pages. DOI:https://doi.org/10.1145/3312575&lt;/p&gt; &lt;p&gt;[2] Michal Ziemski, Marcin Junczys-Dowmunt, and Bruno Pouliquen. 2016. The United Nations parallel corpus v1.0. In&lt;br&gt; Proceedings of the LREC, 2016&lt;/p&gt;</dct:description>
    <dct:description>This work is supported by the Spanish Ministerio de Economía y Competitividad and European Regional Development Fund, through the postdoctoral senior grant Ramón y Cajal.</dct:description>
    <dct:description>{"references": ["Costa-juss\u00e0, M.R., Casas, N., Escolano, C. and Fonollosa, J.A.R., Chinese-Catalan: A Neural Machine Translation Approach based on Pivoting and Attention Mechanisms, ACM Transactions on Asian and Low-Resource Language Information Processing, Vol 18, No 4, Art. 43, 2019", "Michal Ziemski, Marcin Junczys-Dowmunt, and Bruno Pouliquen. 2016. The United Nations parallel corpus v1.0. In Proceedings of the LREC, 2016"]}</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3888414"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.3888414</dcat:accessURL>
        <dcat:byteSize>820376</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/3888414/files/UN_test_ca.txt</dcat:downloadURL>
        <dcat:mediaType>text/plain</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
40
10
views
downloads
All versions This version
Views 4040
Downloads 1010
Data volume 8.2 MB8.2 MB
Unique views 3838
Unique downloads 99

Share

Cite as