@InProceedings{belinkov-glass:2016:VarDial3,
  author    = {Belinkov, Yonatan  and  Glass, James},
  title     = {A Character-level Convolutional Neural Network for Distinguishing Similar Languages and Dialects},
  booktitle = {Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {145--152},
  abstract  = {Discriminating between closely-related language varieties is considered a
	challenging and important task. This paper describes our submission to the DSL
	2016 shared-task, which included two sub-tasks: one on discriminating similar
	languages and one on identifying Arabic dialects. We developed a
	character-level neural network for this task. Given a sequence of characters,
	our model embeds each character in vector space, runs the sequence through
	multiple convolutions with different filter widths, and pools the convolutional
	representations to obtain a hidden vector representation of the text that is
	used for predicting the language or dialect. We primarily focused on the Arabic
	dialect identification task and obtained an F1 score of 0.4834, ranking 6th out
	of 18 participants. We also analyze errors made by our system on the Arabic
	data in some detail, and point to challenges such an approach is faced with.},
  url       = {http://aclweb.org/anthology/W16-4819}
}