---
tags:
- spacy
- token-classification
language:
- de
widget:
- text: Mein Asthma behandle ich mit 10mg Salbutamol.
model-index:
- name: de_GPTNERMED_gbert
  results:
  - task:
      name: NER
      type: token-classification
    metrics:
    - name: NER Precision
      type: precision
      value: 0.9022055764
    - name: NER Recall
      type: recall
      value: 0.9209855565
    - name: NER F Score
      type: f_score
      value: 0.9114988438
---
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](https://doi.org/10.1016/j.jbi.2023.104478) \
The preprint paper is available at: [https://arxiv.org/abs/2208.14493](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](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](https://github.com/frankkramer-lab/GPTNERMED) |

### Label Scheme

<details>

<summary>View label scheme (3 labels for 1 components)</summary>

| Component | Labels |
| --- | --- |
| **`ner`** | `Diagnose`, `Dosis`, `Medikation` |

</details>

### Accuracy

| Type | Score |
| --- | --- |
| `ENTS_F` | 91.15 |
| `ENTS_P` | 90.22 |
| `ENTS_R` | 92.10 |
| `TRANSFORMER_LOSS` | 32882.59 |
| `NER_LOSS` | 56921.35 |