@inproceedings{arnoult-etal-2026-lotusorchid,
    title = "{L}otus{O}rchid at {\#}{SMM}4{H}{--}{H}ea{RD} 2026: Fitting pretrained encoders for {D}utch medical data",
    author = "Arnoult, Sophie  and
      Chen, Shutao  and
      Vossen, Piek",
    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-1.23/",
    pages = "139--145",
    ISBN = "979-8-89176-432-3",
    abstract = "This paper presents our submission to MultiClinAI{'}s NER subtask for {\#}SMM4H-HeaRD 2026. We focus on the questions 1) which Language Model represents the clinical notes best and 2) which annotations can help training these models. To get answers for these questions, we follow a token-based classification approach with pretrained encoder language models, where we compare models that were pretrained on generic data against medical data, and on a single language, Dutch, against many languages. In addition, we present two data-augmented systems: one with data from the other languages of the workshop for multilingual training, and one with synthetic annotations."
}