@inproceedings{zhang-etal-2017-robust,
    title = "Robust Dictionary Lookup in Multiple Noisy Orthographies",
    author = "Zhang, Lingliang  and
      Habash, Nizar  and
      Toussaint, Godfried",
    editor = "Habash, Nizar  and
      Diab, Mona  and
      Darwish, Kareem  and
      El-Hajj, Wassim  and
      Al-Khalifa, Hend  and
      Bouamor, Houda  and
      Tomeh, Nadi  and
      El-Haj, Mahmoud  and
      Zaghouani, Wajdi",
    booktitle = "Proceedings of the Third {A}rabic Natural Language Processing Workshop",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/W17-1315/",
    doi = "10.18653/v1/W17-1315",
    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."
}