@InProceedings{fashwan-alansary:2017:W17-13,
  author    = {Fashwan, Amany  and  Alansary, Sameh},
  title     = {SHAKKIL: An Automatic Diacritization System for Modern Standard Arabic Texts},
  booktitle = {Proceedings of the Third Arabic Natural Language Processing Workshop},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {84--93},
  abstract  = {This paper sheds light on a system that would be able to diacritize Arabic
	texts automatically (SHAKKIL). In this system, the diacritization problem will
	be handled through two levels; morphological and syntactic processing levels.
	The adopted morphological disambiguation algorithm depends on four layers;
	Uni-morphological form layer, rule-based morphological disambiguation layer,
	statistical-based disambiguation layer and Out Of  Vocabulary (OOV) layer. The
	adopted syntactic disambiguation algorithms is concerned with detecting the
	case ending diacritics depending on a rule based approach simulating the
	shallow parsing technique. This will be achieved using an annotated corpus for
	extracting the Arabic linguistic rules, building the language models and
	testing the system output. This system is considered as a good trial of the
	interaction between rule-based approach and statistical approach, where the
	rules can help the statistics in detecting the right diacritization and vice
	versa. At this point, the morphological Word Error Rate (WER) is 4.56% while
	the morphological Diacritic Error Rate (DER) is 1.88% and the syntactic WER is
	9.36%. The best WER is 14.78% compared to the best-published results, of
	(Abandah, 2015); 11.68%, (Rashwan, et al., 2015); 12.90% and (Metwally,
	Rashwan, \& Atiya, 2016); 13.70%.},
  url       = {http://www.aclweb.org/anthology/W17-1311}
}