@inproceedings{adouane-dobnik-2017-identification,
    title = "Identification of Languages in {A}lgerian {A}rabic Multilingual Documents",
    author = "Adouane, Wafia  and
      Dobnik, Simon",
    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://aclanthology.org/W17-1301",
    doi = "10.18653/v1/W17-1301",
    pages = "1--8",
    abstract = "This paper presents a language identification system designed to detect the language of each word, in its context, in a multilingual documents as generated in social media by bilingual/multilingual communities, in our case speakers of Algerian Arabic. We frame the task as a sequence tagging problem and use supervised machine learning with standard methods like HMM and Ngram classification tagging. We also experiment with a lexicon-based method. Combining all the methods in a fall-back mechanism and introducing some linguistic rules, to deal with unseen tokens and ambiguous words, gives an overall accuracy of 93.14{\%}. Finally, we introduced rules for language identification from sequences of recognised words.",
}