@inproceedings{eryani-habash-2021-automatic,
    title = "Automatic {R}omanization of {A}rabic Bibliographic Records",
    author = "Eryani, Fadhl  and
      Habash, Nizar",
    editor = "Habash, Nizar  and
      Bouamor, Houda  and
      Hajj, Hazem  and
      Magdy, Walid  and
      Zaghouani, Wajdi  and
      Bougares, Fethi  and
      Tomeh, Nadi  and
      Abu Farha, Ibrahim  and
      Touileb, Samia",
    booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
    month = apr,
    year = "2021",
    address = "Kyiv, Ukraine (Virtual)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.wanlp-1.23/",
    pages = "213--218",
    abstract = "International library standards require cataloguers to tediously input Romanization of their catalogue records for the benefit of library users without specific language expertise. In this paper, we present the first reported results on the task of automatic Romanization of \textit{undiacritized} Arabic bibliographic entries. This complex task requires the modeling of Arabic phonology, morphology, and even semantics. We collected a 2.5M word corpus of parallel Arabic and Romanized bibliographic entries, and benchmarked a number of models that vary in terms of complexity and resource dependence. Our best system reaches 89.3{\%} exact word Romanization on a blind test set. We make our data and code publicly available."
}