@InProceedings{mukherjee-kubler:2017:RANLP,
  author    = {Mukherjee, Atreyee  and  K\"{u}bler, Sandra},
  title     = {Similarity Based Genre Identification for POS Tagging Experts \& Dependency Parsing},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {519--526},
  abstract  = {POS tagging and dependency parsing achieve good results for homogeneous
	datasets. However, these tasks are much more difficult on heterogeneous
	datasets. In (Mukherjee et al. 2016, 2017), we address this issue by creating
	genre experts for both POS tagging and parsing. We use topic modeling to 
	automatically separate training and test data into genres and to create
	annotation experts per genre by training separate models for each topic.
	However, this approach assumes that topic modeling is performed jointly on
	training and test sentences each time a new test sentence is encountered. We
	extend this work by assigning new test sentences to their genre expert by using
	similarity metrics. We investigate three different types of methods: 1) based
	on words highly associated with a genre by the topic modeler, 2) using a
	k-nearest neighbor classification approach, and  3) using perplexity to
	determine the closest topic. The results show that the choice of similarity
	metric has an effect on results and that we can reach  comparable accuracies to
	the joint topic modeling in POS tagging and dependency parsing, thus providing
	a viable and efficient approach to POS tagging and parsing a sentence by its
	genre expert.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_068}
}