@inproceedings{aloraini-etal-2020-qmul,
    title = "The {QMUL}/{HRBDT} contribution to the {NADI} {A}rabic Dialect Identification Shared Task",
    author = "Aloraini, Abdulrahman  and
      Poesio, Massimo  and
      Alhelbawy, Ayman",
    editor = "Zitouni, Imed  and
      Abdul-Mageed, Muhammad  and
      Bouamor, Houda  and
      Bougares, Fethi  and
      El-Haj, Mahmoud  and
      Tomeh, Nadi  and
      Zaghouani, Wajdi",
    booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.wanlp-1.31/",
    pages = "295--301",
    abstract = "We present the Arabic dialect identification system that we used for the country-level subtask of the NADI challenge. Our model consists of three components: BiLSTM-CNN, character-level TF-IDF, and topic modeling features. We represent each tweet using these features and feed them into a deep neural network. We then add an effective heuristic that improves the overall performance. We achieved an F1-Macro score of 20.77{\%} and an accuracy of 34.32{\%} on the test set. The model was also evaluated on the Arabic Online Commentary dataset, achieving results better than the state-of-the-art."
}