@article{BubenhoferHauptSchwinn2016,
  author    = {Noah Bubenhofer and Stefanie Haupt and Horst Schwinn},
  title     = {A comparable Wikipedia corpus: from wiki syntax to POS tagged XML},
  series   = {[Arbeiten zur Mehrsprachigkeit / B] Arbeiten zur Mehrsprachigkeit = Working papers in multilingualism / Sonderforschungsbereich 538 Mehrsprachigkeit 538, Universit{\"a}t Hamburg},
  number    = {96},
  publisher = {Universit{\"a}t Hamburg},
  address   = {Hamburg},
  issn      = {0176-599X},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-51897},
  pages     = {141 -- 144},
  year      = {2016},
  abstract  = {To build a comparable Wikipedia corpus of German, French, Italian, Norwegian, Polish and Hungarian for contrastive grammar research, we used a set of XSLT stylesheets to transform the mediawiki anntations to XML. Furthermore, the data has been amnntated with word class information using different taggers. The outcome is a corpus with rich meta data and linguistic annotation that can be used for multilingual research in various linguistic topics.},
  language  = {en}
}