Transformer-Based Multilabel NER Using Wikipedia Corpora in Multiple Languages
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250488 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Yelyzaveta Ahapova und 2 weiteren Autor:innen. Beteiligte Einrichtung: IT-Infrastructure for Translational Medical Research, University of Augsburg, Germany. Hauptthemen laut MEDLINE: Natural Language Processing, Internet, Encyclopedias as Topic, Data Mining. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The high cost of manual data labeling and privacy concerns result in a considerable dearth of medical annotations in non-English texts. Recent work by Frank and Kramer [1] introduces an unsupervised approach for constructing an ontology-annotated corpora from Wikipedia (https://www.wikidata.org) for German medical NER. We evaluate the proposed approach across English, German, Spanish, and French for medication and diagnosis entity recognition. Our multilabel corpora yield notable improvements in German medication detection under sparse annotations compared to the baseline, with consistent performance across other languages.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- IT-Infrastructure for Translational Medical Research, University of Augsburg, Germany.
Zitieren
APA
Ahapova, Y., Frei, J., & Kramer, F. (2025). Transformer-Based Multilabel NER Using Wikipedia Corpora in Multiple Languages. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250488
Vancouver
Ahapova Y, Frei J, Kramer F. Transformer-Based Multilabel NER Using Wikipedia Corpora in Multiple Languages. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250488
BibTeX
@article{Ahapova2025,
author = {Ahapova, Yelyzaveta and Frei, Johann and Kramer, Frank},
title = {Transformer-Based Multilabel NER Using Wikipedia Corpora in Multiple Languages},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250488}
}
EUVIMED