Dataset Open Access

Paderborn Genre Analysis Corpus 2012 (PaGA-12)

Baumann, Michael; Lettmann, Theodor; Stein, Benno


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3250070</identifier>
  <creators>
    <creator>
      <creatorName>Baumann, Michael</creatorName>
      <givenName>Michael</givenName>
      <familyName>Baumann</familyName>
      <affiliation>Universität Paderborn</affiliation>
    </creator>
    <creator>
      <creatorName>Lettmann, Theodor</creatorName>
      <givenName>Theodor</givenName>
      <familyName>Lettmann</familyName>
      <affiliation>Bauhaus-Universität Weimar</affiliation>
    </creator>
    <creator>
      <creatorName>Stein, Benno</creatorName>
      <givenName>Benno</givenName>
      <familyName>Stein</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-9033-2217</nameIdentifier>
      <affiliation>Bauhaus-Universität Weimar</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Paderborn Genre Analysis Corpus 2012 (PaGA-12)</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2012</publicationYear>
  <subjects>
    <subject>documents</subject>
    <subject>genre</subject>
    <subject>german</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2012-01-01</date>
  </dates>
  <language>de</language>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3250070</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3250069</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/webis</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
  </descriptions>
</resource>
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