@inproceedings{van-es-2026-dt4h,
    title = "{DT}4{H}.nl at {\#}{SMM}4{H}-{H}ea{RD} 2026: Multilingual Clinical {NER} with multilingual and monolingual models",
    author = "van Es, Bram",
    editor = "Lopez-Garcia, Guillermo  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.14/",
    pages = "82--87",
    ISBN = "979-8-89176-432-3",
    abstract = "We describe the setup we used to complete the MultiClinAI-NER task in the SMM4H-HeaRD workshop 2026. In this work we employed a dedicated multilingual encoder model (EuroBERT-610m), two Dutch encoder models trained from scratch on clinical corpora (MedRoBERTa.nl and CardioDeBERTa.nl) and a generic Dutch encoder model (RobBERT2023-large), all finetuned with a 3-layer DNN head. We find that the use of multilingual datasets is potentially beneficial in augmenting the training corpora of monolingual models."
}