@InProceedings{andrews-EtAl:2017:Long,
  author    = {Andrews, Nicholas  and  Dredze, Mark  and  Van Durme, Benjamin  and  Eisner, Jason},
  title     = {Bayesian Modeling of Lexical Resources for Low-Resource Settings},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {1029--1039},
  abstract  = {Lexical resources such as dictionaries and gazetteers are often used
	as auxiliary data for tasks such as part-of-speech induction and named-entity
	recognition. However, discriminative training with lexical features requires
	annotated data to reliably estimate the lexical feature weights and may result
	in overfitting the lexical features at the expense of features which generalize
	better.
	In this paper, we investigate a more robust approach: we stipulate
	that the lexicon is the result of an assumed generative
	process. Practically, this means that we may treat the lexical
	resources as observations under the proposed generative model.
	The lexical resources provide training data for the generative model
	without requiring separate data to estimate lexical feature
	weights. We evaluate the proposed approach in two settings:
	part-of-speech induction and low-resource named-entity recognition.},
  url       = {http://aclweb.org/anthology/P17-1095}
}