DA-BioNER: data augmentation based on few-shot learning and distant supervision for biomedical named entity recognition
Bioinformatics · 01.06.2026 · 42 (6)
DOI: 10.1093/bioinformatics/btag332 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 22.05.2026. Verfasst von Yesol Park und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Hanyang University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Data Mining, Natural Language Processing, Computational Biology, Machine Learning. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & communications Technology Planning & Evaluation, Artificial Intelligence Graduate School Program, Korea Institute of Marine Science & Technology Promotion.
Abstract (Originalsprache)
Motivation Named entity recognition (NER) is a fundamental component of structured knowledge extraction, yet its effectiveness in emerging domains remains by the scarcity of high-quality, domain-specific annotated corpora. Although data augmentation and distant supervision have been explored to alleviate this issue, existing methods often introduce limited entity diversity, noisy labels, or disrupt contextual integrity, thereby limiting their generalization ability in low-resource settings. Results In this study, we propose DA-BioNER, a context-preserving data expansion framework for biomedical NER. DA-BioNER combines multiple base NER models trained on few-shot data to provide coarse annotations, followed by refinement using a large language model (LLM) guided by global biomedical knowledge. Unlike generation-based augmentation methods that synthesize new sentences, DA-BioNER performs annotation refinement within existing sentences, preserving both syntactic structure and semantic context. By constraining the role of LLM to refinement rather than open-ended generation, the framework effectively reduces hallucination while improving label precision and consistency. We evaluate DA-BioNER on three benchmark datasets (NCBI-Disease, BC5CDR, and BioRED), under low-resource conditions. In 40-shot settings, DA-BioNER achieves F1-scores of 0.750, 0.795, and 0.799, respectively, outperforming state-of-the-art methods, including LSMS, DAGA, and MELM, by up to 0.32. Under more extreme few-shot settings, DA-BioNER further improves F1-scores by up to 0.08, while generating an average of 1,391 additional unique entities, substantially enriching training diversity. These results demonstrate that DA-BioNER provides a scalable and adaptable solution for robust biomedical NER, particularly in domain adaptation and low-resource scenarios. Availability DA-BioNER is publicly available at https://github.com/DMnBI/DA-BioNER.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, Hanyang University, Seoul, Republic of Korea.
- Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea.
- Department of Biomedical Informatics, Hanyang University, Seoul, Republic of Korea.
ORCID-Profile: Mina Rho
Förderung
- Institute of Information & communications Technology Planning & Evaluation
- Artificial Intelligence Graduate School Program
- Korea Institute of Marine Science & Technology Promotion
- Ministry of Oceans and Fisheries
- Fostering Outstanding Universities for Research
- National Research Foundation of Korea
- Korea Basic Science Institute
- National Research Facilities and Equipment Center
Zitieren
APA
Park, Y., Son, G., Kim, T., & Rho, M. (2026). DA-BioNER: data augmentation based on few-shot learning and distant supervision for biomedical named entity recognition. Bioinformatics, 42(6). https://doi.org/10.1093/bioinformatics/btag332
Vancouver
Park Y, Son G, Kim T, Rho M. DA-BioNER: data augmentation based on few-shot learning and distant supervision for biomedical named entity recognition. Bioinformatics. 2026;42(6). doi:10.1093/bioinformatics/btag332
BibTeX
@article{Park2026,
author = {Park, Yesol and Son, Gyujin and Kim, Taeuk and Rho, Mina},
title = {DA-BioNER: data augmentation based on few-shot learning and distant supervision for biomedical named entity recognition},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {6},
doi = {10.1093/bioinformatics/btag332}
}
EUVIMED