metadata
library_name: transformers
tags:
- contrastive-learning
- Spanish-UMLS
- Hierarchical-enrichment
license: mit
language:
- es
base_model:
- PlanTL-GOB-ES/roberta-base-biomedical-es
HERBERT: Leveraging UMLS Hierarchical Knowledge to Enhance Clinical Entity Normalization in Spanish
HERBERT-GP is a contrastive-learning-based bi-encoder for medical entity normalization in Spanish.
It leverages hierarchical relationships from UMLS (parents and grandparents) to enhance the candidate retrieval step for entity linking in Spanish clinical texts.
Key features:
- Base model: PlanTL-GOB-ES/roberta-base-biomedical-clinical-es
- Trained with 15 positive pairs per anchor using synonyms, parents, and grandparents from UMLS/SNOMED-CT.
- Task: Normalization of disease, procedure, and symptom mentions to SNOMED-CT/UMLS codes.
- Domain: Spanish biomedical/clinical texts.
- Corpora: DisTEMIST, MedProcNER, SympTEMIST.
Evaluation (top-k accuracy):
| Corpus | Top-1 | Top-5 | Top-25 | Top-200 |
|---|---|---|---|---|
| DisTEMIST | 0.574 | 0.720 | 0.803 | 0.871 |
| SympTEMIST | 0.630 | 0.779 | 0.886 | 0.949 |
| MedProcNER | 0.655 | 0.767 | 0.840 | 0.894 |