@inproceedings{das-etal-2026-vinland,
    title = "{V}inland{\_}{V}ector at {\#}{SMM}4{H}-{H}ea{RD} 2026: Multilingual {ADE} Detection and Query-Augmented Clinical {NER} for {E}nglish",
    author = "Das, Nirjhar  and
      Aich, Rathijit  and
      Chowdhury, Mahfuzulhoq",
    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-1.33/",
    pages = "211--215",
    ISBN = "979-8-89176-432-3",
    abstract = "In this paper, we address Task 1 on adverse drug event (ADE) detection and Task 8 on MultiClinNER at SMM4H-HeaRD 2026. ADE detection is formulated as a multilingual binary classification problem over social media posts spanning German, French, Russian, English, Mandarin and Japanese, with zero-shot on Farsi. Using XLM-RoBERTa-Large with a dual-pooling head, combined with stratified sampling, language-conditioned inputs, translation-based augmentation, and calibrated ensembling, our model achieves a macro F1 score of 0.6088, surpassing both the competition mean (0.5465) and median (0.5798). Our work in MultiClinNER targets clinical NER for English text. Using GLiNER-large with sliding-window inference, query augmentation, and calibrated thresholds, it achieves strict F1 scores of 0.7591 (Disease), 0.7263 (Procedure), and 0.6733 (Symptom), outperforming a PubMedBERT baseline across all entities."
}