@inproceedings{cocchieri-etal-2025-openbioner,
    title = "{O}pen{B}io{NER}: Lightweight Open-Domain Biomedical Named Entity Recognition Through Entity Type Description",
    author = "Cocchieri, Alessio  and
      Frisoni, Giacomo  and
      Mart{\'i}nez Galindo, Marcos  and
      Moro, Gianluca  and
      Tagliavini, Giuseppe  and
      Candoli, Francesco",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.47/",
    pages = "818--837",
    ISBN = "979-8-89176-195-7",
    abstract = "Biomedical Named Entity Recognition (BioNER) faces significant challenges in real-world applications due to limited annotated data and the constant emergence of new entity types, making zero-shot learning capabilities crucial. While Large Language Models (LLMs) possess extensive domain knowledge necessary for specialized fields like biomedicine, their computational costs often make them impractical. To address these challenges, we introduce OpenBioNER, a lightweight BERT-based cross-encoder architecture that can identify any biomedical entity using only its description, eliminating the need for retraining on new, unseen entity types. Through comprehensive evaluation on established biomedical benchmarks, we demonstrate that OpenBioNER surpasses state-of-the-art baselines, including specialized 7B NER LLMs and GPT-4o, achieving up to 10{\%} higher F1 scores while using 110M parameters only. Moreover, OpenBioNER outperforms existing small-scale models that match textual spans with entity types rather than descriptions, both in terms of accuracy and computational efficiency."
}