@inproceedings{alshargi-etal-2019-morphologically,
    title = "Morphologically Annotated Corpora for Seven {A}rabic Dialects: {T}aizi, {S}anaani, {N}ajdi, {J}ordanian, {S}yrian, {I}raqi and {M}oroccan",
    author = "Alshargi, Faisal  and
      Dibas, Shahd  and
      Alkhereyf, Sakhar  and
      Faraj, Reem  and
      Abdulkareem, Basmah  and
      Yagi, Sane  and
      Kacha, Ouafaa  and
      Habash, Nizar  and
      Rambow, Owen",
    editor = "El-Hajj, Wassim  and
      Belguith, Lamia Hadrich  and
      Bougares, Fethi  and
      Magdy, Walid  and
      Zitouni, Imed  and
      Tomeh, Nadi  and
      El-Haj, Mahmoud  and
      Zaghouani, Wajdi",
    booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/W19-4615/",
    doi = "10.18653/v1/W19-4615",
    pages = "137--147",
    abstract = "We present a collection of morphologically annotated corpora for seven Arabic dialects: Taizi Yemeni, Sanaani Yemeni, Najdi, Jordanian, Syrian, Iraqi and Moroccan Arabic. The corpora collectively cover over 200,000 words, and are all manually annotated in a common set of standards for orthography, diacritized lemmas, tokenization, morphological units and English glosses. These corpora will be publicly available to serve as benchmarks for training and evaluating systems for Arabic dialect morphological analysis and disambiguation."
}