@inproceedings{silva-etal-2026-multitask,
    title = "A Multitask Transformer for Offensive Language Detection and Target Identification in {H}ate{BR}",
    author = "Silva, Guilherme  and
      Silva, Pedro  and
      Peixoto, Matheus  and
      Moreira, Gladston  and
      Luz, Eduardo",
    editor = "Souza, Marlo  and
      de-Dios-Flores, Iria  and
      Santos, Diana  and
      Freitas, Larissa  and
      Souza, Jackson Wilke da Cruz  and
      Ribeiro, Eug{\'e}nio",
    booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
    month = apr,
    year = "2026",
    address = "Salvador, Brazil",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-dnd/2026.propor-1.109/",
    pages = "1049--1054",
    ISBN = "979-8-89176-387-6",
    abstract = "Hate speech detection is often treated as a binary task, ignoring the hierarchical nature of toxicity, such as severity levels and specific target groups. This work presents a Multitask Learning (MTL) approach for the HateBR dataset, utilizing a shared BERTimbau encoder to simultaneously predict binary offensiveness, ordinal severity, and hate speech targets. Our experiments demonstrate that the MTL architecture outperforms Single-Task baselines on the primary offensive detection task, increasing the Matthews Correlation Coefficient from 0.80 to 0.82. Beyond predictive performance, we show that joint training implicitly enforces hierarchical sanity: the unified model yields a 0{\%} target-inconsistency rate (i.e., no cases where a comment is predicted \textit{Non-offensive} while still assigned a hate target). However, we observe negative transfer in the fine-grained multilabel target task (Micro-F1 drops from 0.59 to 0.42), highlighting a trade-off between logical consistency and target attribution under extreme imbalance."
}