@inproceedings{qachfar-etal-2024-detectiveredasers,
    title = "{D}etective{R}e{DAS}ers at {HSD}-2{L}ang 2024: A New Pooling Strategy with Cross-lingual Augmentation and Ensembling for Hate Speech Detection in Low-resource Languages",
    author = "Qachfar, Fatima Zahra  and
      Tuck, Bryan  and
      Verma, Rakesh",
    editor = {H{\"u}rriyeto{\u{g}}lu, Ali  and
      Tanev, Hristo  and
      Thapa, Surendrabikram  and
      Uludo{\u{g}}an, G{\"o}k{\c{c}}e},
    booktitle = "Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024)",
    month = mar,
    year = "2024",
    address = "St. Julians, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.case-1.28/",
    pages = "199--204",
    abstract = "This paper addresses hate speech detection in Turkish and Arabic tweets, contributing to the HSD-2Lang Shared Task. We propose a specialized pooling strategy within a soft-voting ensemble framework to improve classification in Turkish and Arabic language models. Our approach also includes expanding the training sets through cross-lingual translation, introducing a broader spectrum of hate speech examples. Our method attains F1-Macro scores of 0.6964 for Turkish (Subtask A) and 0.7123 for Arabic (Subtask B). While achieving these results, we also consider the computational overhead, striking a balance between the effectiveness of our unique pooling strategy, data augmentation, and soft-voting ensemble. This approach advances the practical application of language models in low-resource languages for hate speech detection."
}