@inproceedings{nguyen-danilova-2026-enhanced,
    title = "An Enhanced Training-Free Pipeline for Entity Recognition and Linking: A Low-Resource Case Study {--} 20-th Century Historical Medical Texts",
    author = "Nguyen, Phu-Vinh  and
      Danilova, Vera",
    editor = {Danilova, Vera  and
      Kurfal{\i}, Murathan  and
      S{\"o}derfeldt, Ylva  and
      Reed, Julia  and
      Burchell, Andrew},
    booktitle = "Proceedings of the 1st Workshop on Linguistic Analysis for Health ({H}ea{L}ing 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.healing-1.8/",
    pages = "94--104",
    ISBN = "979-8-89176-367-8",
    abstract = "Entity linking in biomedicine typically relies on large annotated corpora and supervised methods, which often fail in out-of-distribution settings. Historical medical texts are rich in biomedical terms but pose unique challenges: terminology has changed, some concepts are obsolete, and stylistic differences from modern journals prevent off-the-shelf models fine-tuned on contemporary datasets from aligning historical terms with current ontologies. Training-free methods based on LLMs offer a solution by linking historical terms to modern concepts and inferring their meaning from context. In this paper, we evaluate a state-of-the-art training-free entity linking method on historical medical texts and propose an improved pipeline{---}end-to-end entity extraction and linking with confidence estimation. We also assess performance on modern benchmarks to check whether the gains generalize to other domains and show their superior performance in most cases. We report an analysis of the findings. The code and curated dataset for historical medical entity linking are available on GitHub."
}