@inproceedings{RehbeinvanGenabith2017,
  author    = {Ines Rehbein and Josef van Genabith},
  title     = {Why is it so difficult to compare treebanks? TIGER and T{\"u}Ba-D/Z revisited},
  series = {The Sixth International Workshop on Treebanks and Linguistic Theories (TLT ‘07). Bergen, Norway. December 7–8, 2007},
  editor    = {Koenraad De Smedt and Jan Hajič and Sandra K{\"u}bler},
  publisher = {Northern European Association for Language Technology},
  address   = {Tartu},
  issn      = {1736-6305},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-57822},
  pages     = {115 -- 126},
  year      = {2017},
  abstract  = {This paper is a contribution to the ongoing discussion on treebank annotation schemes and their impact on PCFG parsing results. We provide a thorough comparison of two German treebanks: the TIGER treebank and the T{\"u}Ba-D/Z. We use simple statistics on sentence length and vocabulary size, and more refined methods such as perplexity and its correlation with PCFG parsing results, as well as a Principal Components Analysis. Finally we present a qualitative evaluation of a set of 100 sentences from the T{\"u}Ba- D/Z, manually annotated in the TIGER as well as in the T{\"u}Ba-D/Z annotation scheme, and show that even the existence of a parallel subcorpus does not support a straightforward and easy comparison of both annotation schemes.},
  language  = {en}
}