@inproceedings{alizada-dubossarsky-2026-benchmarking,
    title = "Benchmarking Hate Speech Detection in {A}zerbaijani with {T}urkish Cross-Lingual Transfer and Transformer Models",
    author = "Alizada, Tural  and
      Dubossarsky, Haim",
    editor = {Oflazer, Kemal  and
      K{\"o}ksal, Abdullatif  and
      Varol, Onur},
    booktitle = "Proceedings of the Second Workshop Natural Language Processing for {T}urkic Languages ({SIGTURK} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.sigturk-1.10/",
    pages = "103--112",
    ISBN = "979-8-89176-370-8",
    abstract = "In this paper, we investigated the task of hate-speech classification in the closely related Turkic language pair, Turkish-Azerbaijani. Transformer models can achieve strong hate-speech classification in Turkish, but their performance does not reliably transfer to closely related low-resource languages without careful evaluation. We study Turkish{--}Azerbaijani hate speech detection and introduce the first manually annotated Azerbaijani benchmark, comprising 1,112 YouTube comments from major news channels with severe class imbalance. We compare XLM-RoBERTa and a compact BERT-Tiny model against a TF{--}IDF + logistic regression baseline under monolingual training, zero-shot Turkish{\textrightarrow}Azerbaijani transfer, low-resource balanced subsampling, bilingual mixed fine-tuning, and translation-based augmentation using machine-translated Turkish data. XLM-R attains high macro-F1 in Turkish and achieves moderate zero-shot transfer to Azerbaijani, but native Azerbaijani training is fragile for the hate class. Mixed bilingual training improves robustness for both languages, whereas TF{--}IDF generalizes poorly to Azerbaijani."
}