@inproceedings{floresca-etal-2026-forgotten,
    title = "Forgotten Words: Benchmarking {N}eo{BERT} for Dementia Detection in Low-Resource Conversational {F}ilipino and {E}nglish Speech",
    author = "Floresca, Rez Samantha  and
      Hao, Edric Castel  and
      Bu{\~n}ales, Hannah Grachiella  and
      Temprosa, Chelsea Dominique  and
      Reyes, Georgianna  and
      Chua, Kervin Gabriel",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "{B}io{NLP} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-1.83/",
    pages = "1029--1040",
    ISBN = "979-8-89176-434-7",
    abstract = "Dementia detection from spontaneous speech offers a scalable approach to cognitive screening, yet NLP systems remain predominantly English-centric. This limitation is especially acute in the Philippines, where Filipino?English code-switching is pervasive and no prior work has addressed NLP-based dementia detection.We present the first systematic evaluation of transformer-based dementia detection in Filipino speech and the first assessment of NeoBERT in a clinical NLP setting. To separate language from domain effects, we construct a parallel bilingual dataset of 4,000 DementiaBank-derived transcripts, with Filipino translations produced manually to preserve discourse-level markers of cognitive decline. We evaluate five model families, TF-IDF + LogReg, BERT, NeoBERT, XLM-R, and RoBERTa-Tagalog, under monolingual, zero-shot cross-lingual, and bilingual fine-tuning settings. We find that in-domain performance does not transfer across languages, with English-trained BERT dropping to Macro-F1 = 0.455 on Filipino, and that architectural modernization alone does not improve robustness. Bilingual fine-tuning, however, eliminates cross-lingual degradation across all transformer models, converging to Macro-F1 = 0.969{--}0.973. These results suggest that multilingual clinical NLP performance is driven primarily by linguistic coverage during training rather than model scale or architecture."
}