Dataset Open Access

Wikipedia biographies

Blouin Baptiste; Magistry Pierre; Van den Bosch Nora


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <controlfield tag="005">20201001123301.0</controlfield>
  <controlfield tag="001">4059194</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aix-Marseille University</subfield>
    <subfield code="0">(orcid)0000-0002-9296-8902</subfield>
    <subfield code="a">Magistry Pierre</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aix-Marseille University</subfield>
    <subfield code="0">(orcid)0000-0002-1881-5801</subfield>
    <subfield code="a">Van den Bosch  Nora</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1142394588</subfield>
    <subfield code="z">md5:7e8bcbcd7bd6ede5a747f9cbd7b2fa9f</subfield>
    <subfield code="u">https://zenodo.org/record/4059194/files/Biographies_12_08_2020.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-09-29</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:4059194</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Aix-Marseille University</subfield>
    <subfield code="0">(orcid)0000-0002-7171-3628</subfield>
    <subfield code="a">Blouin Baptiste</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Wikipedia biographies</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Folder containing biographies from Wikipedia. The folder is composed of two subfolders, one containing the Chinese biographies and one containing the English biographies. Each of these subfolders contains one subfolder for each biography (represented by its Wikipedia ID) and each of these folders contains 2 files, one in xml format representing the textual content of the biography and another in csv format containing information about the named entities present in the biography.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.4058306</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.4059194</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
680
31
views
downloads
All versions This version
Views 680381
Downloads 3116
Data volume 35.4 GB18.3 GB
Unique views 581324
Unique downloads 2816

Share

Cite as