Gbert-based model of the GPTNERMED German NER model for medical entities.
See our published paper at: https://doi.org/10.1016/j.jbi.2023.104478
The preprint paper is available at: https://arxiv.org/abs/2208.14493
If you like our work, give us a star on our GitHub repository: https://github.com/frankkramer-lab/GPTNERMED
Feature | Description |
---|---|
Name | de_GPTNERMED_gbert |
Version | 1.0.0 |
spaCy | >=3.4.1,<3.5.0 |
Default Pipeline | transformer , ner |
Components | transformer , ner |
Vectors | 0 keys, 0 unique vectors (0 dimensions) |
Sources | n/a |
License | n/a |
Author | Johann Frei |
Label Scheme
View label scheme (3 labels for 1 components)
Component | Labels |
---|---|
ner |
Diagnose , Dosis , Medikation |
Accuracy
Type | Score |
---|---|
ENTS_F |
91.15 |
ENTS_P |
90.22 |
ENTS_R |
92.10 |
TRANSFORMER_LOSS |
32882.59 |
NER_LOSS |
56921.35 |
- Downloads last month
- 15
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Evaluation results
- NER Precisionself-reported0.902
- NER Recallself-reported0.921
- NER F Scoreself-reported0.911