@inproceedings{tien-van-2026-dnt,
    title = "{DNT} at {\#}{SMM}4{H}{--}{H}ea{RD} 2026: Leveraging {BERT}-based Encoders and {LLM}s for Medical Information Extraction",
    author = "Tien, Doan Nhat  and
      V{\u{a}}n, Th{\`i}n {\DJ}ặng",
    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-1.7/",
    pages = "36--40",
    ISBN = "979-8-89176-432-3",
    abstract = "This paper presents our systems for two tasks at {\#}SMM4H-HeaRD 2026. For Task 1 (multilingual Adverse Drug Event detection), we fine-tune BERT-based multilingual models (InfoXLM and XLM-RoBERTa) and Qwen3.5-9B with ensemble methods, achieving 0.8584 macro F1 on the development set and 0.5304 F1 on unseen Farsi. For Task 7 (span detection of ClinicalImpacts and SocialImpacts in opioid narratives), DeBERTa-Large with simplified labeling achieves the best test performance (0.583 relaxed F1, 0.500 strict F1). Our analysis shows that LLMs excel on known languages in Task 1, while transformer-based models with simplified labeling generalize better for NER tasks."
}