@inproceedings{pinar-etal-2026-sinai,
    title = "{SINAI} at {\#}{SMM}4{H}{--}{H}ea{RD} 2026: Multilingual Clinical {NER} with {M}r{BERT}-biomed and Optuna Hyperparameter Optimization",
    author = "Pi{\~n}ar, Lucas Molino  and
      Diaz-Galiano, Manuel Carlos  and
      Mart{\'i}n-Valdivia, Mar{\'i}a-Teresa",
    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-1.4/",
    pages = "18--22",
    ISBN = "979-8-89176-432-3",
    abstract = "This paper describes the system submitted by our team to the MultiClinAI shared task at the 11th SMM4H-HeaRD Workshop (ACL 2026). The task addresses multilingual clinical Named Entity Recognition (NER) for three entity types (Disease, Procedure, and Symptom) in Spanish clinical texts. Our approach fine-tunes MrBERT-biomed, a domain-adapted ModernBERT model pre-trained on biomedical corpora, using multilingual clinical data from seven European languages. We train independent entity-specific models, each optimized via Bayesian hyperparameter search with Optuna, and apply a deterministic post-processing step that aligns predicted spans to word boundaries. On the official test set, our system achieves overall strict micro-F1 scores of 0.7453, 0.7107, and 0.6603 for Disease, Procedure, and Symptom, respectively."
}