@InProceedings{vandergoot-plank-nissim:2017:WNUT,
  author    = {van der Goot, Rob  and  Plank, Barbara  and  Nissim, Malvina},
  title     = {To normalize, or not to normalize: The impact of normalization on Part-of-Speech tagging},
  booktitle = {Proceedings of the 3rd Workshop on Noisy User-generated Text},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {31--39},
  abstract  = {Does normalization help Part-of-Speech (POS) tagging accuracy on noisy,
	non-canonical data?
	To the best of our knowledge, little is known on the actual impact of
	normalization in a real-world scenario, where gold error detection is not
	available.  We investigate the effect of automatic normalization on POS tagging
	of tweets.
	We also compare normalization to strategies that leverage large amounts of
	unlabeled data kept in its raw form.  Our results show that normalization
	helps, but does not add  consistently beyond just word embedding layer
	initialization. The latter approach yields a tagging model that is competitive
	with a Twitter state-of-the-art tagger.},
  url       = {http://www.aclweb.org/anthology/W17-4404}
}