@InProceedings{tursun-cakici:2017:WNUT,
  author    = {Tursun, Osman  and  Cakici, Ruket},
  title     = {Noisy Uyghur Text Normalization},
  booktitle = {Proceedings of the 3rd Workshop on Noisy User-generated Text},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {85--93},
  abstract  = {Uyghur is the second largest and most actively used social media language in
	China. However, a non-negligible part of Uyghur text appearing in social media
	is unsystematically written with the Latin alphabet, and it continues to
	increase in size. Uyghur text in this format is incomprehensible and ambiguous
	even to native Uyghur speakers. In addition, Uyghur texts in this form lack the
	potential for any kind of advancement for the NLP tasks related to the Uyghur
	language. Restoring and preventing noisy Uyghur text written with unsystematic
	Latin alphabets will be essential to the protection of Uyghur language and
	improving the accuracy of Uyghur NLP tasks. To this purpose, in this work we
	propose and compare the noisy channel model and the neural encoder-decoder
	model as normalizing methods.},
  url       = {http://www.aclweb.org/anthology/W17-4412}
}