Dataset Information
Domain and Language adaptive pre-training of BERT models for Korean-English bilingual clinical text analysis.
Ontology highlight
ABSTRACT:
SUBMITTER: Jo E
PROVIDER: S-EPMC12648908 | biostudies-literature | 2025 Nov
REPOSITORIES: biostudies-literature
Publications
Domain and Language adaptive pre-training of BERT models for Korean-English bilingual clinical text analysis.
BMC medical informatics and decision making 20251125 1
OBJECTIVE: To develop bilingual Korean-English medical language models through domain- and language-adaptive pre-training and evaluate their performance in clinical text analysis tasks, specifically semantic similarity and multi-label classification. METHODS: A bilingual corpus comprising Korean (medical textbooks and online health articles) and English (medical textbooks, health-related articles, and MIMIC-IV EHRs) clinical texts were constructed. Three BERT-based foundation models (Korea Medic ...[more]