Dataset Open Access

Paderborn Genre Analysis Corpus 2012 (PaGA-12)

Baumann, Michael; Lettmann, Theodor; Stein, Benno


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">deu</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">documents</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">genre</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">german</subfield>
  </datafield>
  <controlfield tag="005">20200121072305.0</controlfield>
  <controlfield tag="001">3250070</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Bauhaus-Universität Weimar</subfield>
    <subfield code="a">Lettmann, Theodor</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Bauhaus-Universität Weimar</subfield>
    <subfield code="0">(orcid)0000-0001-9033-2217</subfield>
    <subfield code="a">Stein, Benno</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">20673121</subfield>
    <subfield code="z">md5:c9652cb695e35698fe0459a2bc6b6aa3</subfield>
    <subfield code="u">https://zenodo.org/record/3250070/files/corpus-paga-12.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2012-01-01</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="p">user-webis</subfield>
    <subfield code="o">oai:zenodo.org:3250070</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Universität Paderborn</subfield>
    <subfield code="a">Baumann, Michael</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Paderborn Genre Analysis Corpus 2012 (PaGA-12)</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-webis</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;The Paderborn Genre Analysis 2012 corpus (PaGA-12) contains 1,639 HTML documents of 26 genres. All documents were collected from 2009-10-18 to 2009-11-20, and each document is manually assigned to exactly one genre. For each genre, the corpus provides at least 50 documents.&lt;/p&gt;

&lt;p&gt;All HTML documents contain German text only, and framesets are removed. The corpus is delivered in form of a MySQL database dump; the database structure is detailed in a README file delivered with the corpus.&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.3250069</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3250070</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
184
19
views
downloads
All versions This version
Views 184183
Downloads 1919
Data volume 392.8 MB392.8 MB
Unique views 166165
Unique downloads 1515

Share

Cite as