Dataset Open Access

Parallel Translations from the English Wiktionary

Tresoldi, Tiago


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:cnt="http://www.w3.org/2011/content#" 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.1286991">
    <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.1286991</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.1286991"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-2863-1467">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Tresoldi, Tiago</foaf:name>
        <foaf:givenName>Tiago</foaf:givenName>
        <foaf:familyName>Tresoldi</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Max Planck Institute for the Science of Human History</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Parallel Translations from the English Wiktionary</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">2018</dct:issued>
    <dcat:keyword>translation</dcat:keyword>
    <dcat:keyword>wiktionary</dcat:keyword>
    <dcat:keyword>language comparison</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/715618/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2018-06-11</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/1286991"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/1286991</skos:notation>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.1286990"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/calc"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/dighl"/>
    <owl:versionInfo>20180601</owl:versionInfo>
    <dct:description>&lt;p&gt;Parallel translations from English words and expressions as extracted from the English Wiktionary (database version of 2018-06-01). The data includes 2,169,063 different entries from the translation of 149,530 English words and expressions in 2,358 languages (with much variation in vocabulary size among languages: 931 languages have only one entry and German, the largest language after English, 97,091 entries). Data is offered in a tabular textual format, and all entries include (a) a unique ID, (b) a concept ID referring to the source English word, (c) a description string with the English source and a short definition (such as &amp;ldquo;dictionary/publication that explains the meanings of an ordered list of words&amp;ldquo;), (d) a language ID from the Glottolog catalog, (e) the text of the translation as given in the Wiktionary, and (f) an extra field holding complementary information, when available (such as phonetic transcription of the text, noun gender, etc.). Data is also offer in a set of files (tabular textual files, bibtex sources, and JSON metadata) following the Cross-Linguistic Data Formats (CLDF), a specification designed to allow the exchange of cross-linguistic data.&lt;/p&gt; &lt;p&gt;Code for the extraction is available at http://github.com/tresoldi/wiktionary_parser and a longer description in a blog post of our group, at https://calc.hypotheses.org/?p=32&lt;/p&gt;</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="http://creativecommons.org/licenses/by-sa/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.1286991"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/715618/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">715618</dct:identifier>
    <dct:title>Computer-Assisted Language Comparison: Reconciling Computational and Classical Approaches in Historical Linguistics</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
314
126
views
downloads
All versions This version
Views 314314
Downloads 126126
Data volume 9.5 GB9.5 GB
Unique views 292292
Unique downloads 105105

Share

Cite as