English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Book Chapter

Modeling Communicative Purpose with Functional Style: Corpus and Features for German Genre and Register Analysis

MPS-Authors
/persons/resource/persons209101

Haider,  Thomas
Department of Language and Literature, Max Planck Institute for Empirical Aesthetics, Max Planck Society;

External Ressource
No external resources are shared
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Haider, T., & Palmer, A. (2017). Modeling Communicative Purpose with Functional Style: Corpus and Features for German Genre and Register Analysis. In Proceedings of the Workshop on Stylistic Variation, EMNLP 2017 (pp. 74-84). Copenhagen, Stroudsburg, PA: Association for Computational Linguistics.


Cite as: http://hdl.handle.net/11858/00-001M-0000-002D-E326-1
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 hierarchicaltaxonomy of discourse functions. We implement the taxonomy by developing a new text genre corpus of contemporary German to perform a text based comparativeregister 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.