@inproceedings{saeed-etal-2020-osact4,
    title = "{OSACT}4 Shared Tasks: Ensembled Stacked Classification for Offensive and Hate Speech in {A}rabic Tweets",
    author = "Saeed, Hafiz Hassaan  and
      Calders, Toon  and
      Kamiran, Faisal",
    editor = "Al-Khalifa, Hend  and
      Magdy, Walid  and
      Darwish, Kareem  and
      Elsayed, Tamer  and
      Mubarak, Hamdy",
    booktitle = "Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resource Association",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.osact-1.11/",
    pages = "71--75",
    language = "eng",
    ISBN = "979-10-95546-51-1",
    abstract = "In this paper, we describe our submission for the OCAST4 2020 shared tasks on offensive language and hate speech detection in the Arabic language. Our solution builds upon combining a number of deep learning models using pre-trained word vectors. To improve the word representation and increase word coverage, we compare a number of existing pre-trained word embeddings and finally concatenate the two empirically best among them. To avoid under- as well as over-fitting, we train each deep model multiple times, and we include the optimization of the decision threshold into the training process. The predictions of the resulting models are then combined into a tuned ensemble by stacking a classifier on top of the predictions by these base models. We name our approach {\textquotedblleft}ESOTP{\textquotedblright} (Ensembled Stacking classifier over Optimized Thresholded Predictions of multiple deep models). The resulting ESOTP-based system ranked 6th out of 35 on the shared task of Offensive Language detection (sub-task A) and 5th out of 30 on Hate Speech Detection (sub-task B)."
}