Translating UMLS Concepts to Improve Medical Entity Linking in French: A SapBERT-Based Approach
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250484 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Amaury Fierens und 2 weiteren Autor:innen. Beteiligte Einrichtung: ICTEAM, Louvain School of Engineering, UCLouvain, Belgium. Hauptthemen laut MEDLINE: Unified Medical Language System, Translating, Natural Language Processing, Medical Record Linkage. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Medical Entity Linking (MEL) refers to the task of automatically detecting and codifying medical concepts, which is an important preprocessing step for exploiting unstructured medical reports. SapBERT is an efficient MEL method for the English language. Unfortunately, its cross-language counterpart underperforms in French due to the lack of training data. To address this limitation, this paper explores the possibility of training SapBERT on machine-generated French translations of the UMLS Metathesaurus. Evaluation on the QuaeroFrenchMed benchmark demonstrates that this approach outperforms Cross-lingual SapBERT for SNOMED-CT MEL on the QuaeroFrenchMed benchmark.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- ICTEAM, Louvain School of Engineering, UCLouvain, Belgium.
- Cliniques Universitaires Saint-Luc & NMSK Lab, IREC, UCLouvain, Belgium.
Zitieren
APA
Fierens, A., Englebert, A., & Jodogne, S. (2025). Translating UMLS Concepts to Improve Medical Entity Linking in French: A SapBERT-Based Approach. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250484
Vancouver
Fierens A, Englebert A, Jodogne S. Translating UMLS Concepts to Improve Medical Entity Linking in French: A SapBERT-Based Approach. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250484
BibTeX
@article{Fierens2025,
author = {Fierens, Amaury and Englebert, Alexandre and Jodogne, Sébastien},
title = {Translating UMLS Concepts to Improve Medical Entity Linking in French: A SapBERT-Based Approach},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250484}
}
EUVIMED