@InProceedings{haider-palmer:2017:StyVa,
  author    = {Haider, Thomas  and  Palmer, Alexis},
  title     = {Modeling Communicative Purpose with Functional Style: Corpus and Features for German Genre and Register Analysis},
  booktitle = {Proceedings of the Workshop on Stylistic Variation},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {74--84},
  abstract  = {While there is wide acknowledgement in NLP of the utility of document
	characterization by genre, it is quite difficult to determine a definitive set
	of features or even a comprehensive list of
	genres. This paper addresses both issues. First, with prototype semantics, we
	develop a hierarchical taxonomy of discourse functions. We implement the
	taxonomy by developing a new text genre corpus of contemporary German to
	perform a text based comparative register analysis.
	Second, we extract a host of style features, both deep and shallow, aiming
	beyond linguistically motivated features at situational correlates in texts. 
	The feature sets are used for supervised text genre classification, on which
	our models achieve high accuracy. 
	The combination of the corpus typology and feature sets allows us to
	characterize types of communicative purpose in a comparative setup, by
	qualitative interpretation of style feature loadings of a regularized
	discriminant analysis.
	Finally, to determine the dependence of genre on topics (which are arguably the
	distinguishing factor of sub-genre), we compare and combine our style models
	with Latent Dirichlet Allocation features across different corpus settings with
	unstable topics.},
  url       = {http://www.aclweb.org/anthology/W17-4910}
}