@inproceedings{WestpfahlSchmidt2016,
  author    = {Swantje Westpfahl and Thomas Schmidt},
  title     = {FOLK-Gold ― A gold standard for part-of-speech-tagging of spoken German},
  series = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portorož, Slovenia},
  editor    = {Nicoletta Calzolari and Khalid Choukri and Thierry Declerck and Sara Goggi and Marko Grobelnik and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association (ELRA)},
  address   = {Paris},
  isbn      = {978-2-9517408-9-1},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-50786},
  pages     = {1493 -- 1499},
  year      = {2016},
  abstract  = {In this paper, we present a GOLD standard of part-of-speech tagged transcripts of spoken German. The GOLD standard data consists of four annotation layers – transcription (modified orthography), normalization (standard orthography), lemmatization and POS tags – all of which have undergone careful manual quality control. It comes with guidelines for the manual POS annotation of transcripts of German spoken data and an extended version of the STTS (Stuttgart T{\"u}bingen Tagset) which accounts for phenomena typically found in spontaneous spoken German. The GOLD standard was developed on the basis of the Research and Teaching Corpus of Spoken German, FOLK, and is, to our knowledge, the first such dataset based on a wide variety of spontaneous and authentic interaction types. It can be used as a basis for further development of language technology and corpus linguistic applications for German spoken language.},
  language  = {en}
}