@InProceedings{zhang-habash-toussaint:2017:W17-13,
  author    = {Zhang, Lingliang  and  Habash, Nizar  and  Toussaint, Godfried},
  title     = {Robust Dictionary Lookup in Multiple Noisy Orthographies},
  booktitle = {Proceedings of the Third Arabic Natural Language Processing Workshop},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {119--129},
  abstract  = {We present the MultiScript Phonetic Search algorithm to address the problem of
	language learners looking up unfamiliar words that they heard. We apply it to
	Arabic dictionary lookup with noisy queries done using both the Arabic and
	Roman scripts. Our algorithm is based on a computational phonetic distance
	metric that can be optionally machine learned. To benchmark our performance, we
	created the ArabScribe dataset, containing 10,000 noisy transcriptions of
	random Arabic dictionary words. Our algorithm outperforms Google Translate's
	``did you mean" feature, as well as the Yamli smart Arabic keyboard.},
  url       = {http://www.aclweb.org/anthology/W17-1315}
}