@inproceedings{vandici-etal-2026-multi,
    title = "Multi-Label Polarization Classification with tw{HIN}-{BERT} and {SCUT} Threshold Optimization",
    author = {Vandici, Ilinca  and
      J{\o}ssing, {\r{A}}dne  and
      Viest{\"a}dt, Lukas},
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.356/",
    pages = "2830--2837",
    ISBN = "979-8-89176-414-9",
    abstract = "Tackling task 2, we fine tune a BERT-style encoder with classification heads added on top. We first try out different pre-trained encoder models, before settling on the Twhin-bert multilingual model, since its pretraining corpus (mainly tweets) provides a suitable starting point for our task. To resolve the issue of diverging label annotation styles, we apply the S-Cut algorithm, in order to calibrate thresholds for label selection, and examine its impact. We take a look at the resulting hidden representations in a reduced dimensional space, and examine the linguistic information encoded by our model after fine-tuning using linguistic probing."
}