@inproceedings{pokrywka-jassem-2024-kubapok,
    title = "kubapok@{LT}-{EDI} 2024: Evaluating Transformer Models for Hate Speech Detection in {T}amil",
    author = "Pokrywka, Jakub  and
      Jassem, Krzysztof",
    editor = {Chakravarthi, Bharathi Raja  and
      B, Bharathi  and
      Buitelaar, Paul  and
      Durairaj, Thenmozhi  and
      Kov{\'a}cs, Gy{\"o}rgy  and
      Garc{\'i}a Cumbreras, Miguel {\'A}ngel},
    booktitle = "Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion",
    month = mar,
    year = "2024",
    address = "St. Julian's, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2024.ltedi-1.22/",
    pages = "196--199",
    abstract = "We describe the second-place submission for the shared task organized at the Fourth Workshop on Language Technology for Equality, Diversity, and Inclusion (LT-EDI-2024). The task focuses on detecting caste/migration hate speech in Tamil. The included texts involve the Tamil language in both Tamil script and transliterated into Latin script, with some texts also in English. Considering different scripts, we examined the performance of 12 transformer language models on the dev set. Our analysis revealed that for the whole dataset, the model google/muril-large-cased performs the best. We used an ensemble of several models for the final challenge submission, achieving 0.81 for the test dataset."
}