Token Classification
Transformers
Safetensors
xlm-roberta
ner
named-entity-recognition
clinical-ner
biomedical-ner
multilingual
Instructions to use BSC-NLP4BIA/DT4H_XLM-R_stl_multilingual_disease with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BSC-NLP4BIA/DT4H_XLM-R_stl_multilingual_disease with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="BSC-NLP4BIA/DT4H_XLM-R_stl_multilingual_disease")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("BSC-NLP4BIA/DT4H_XLM-R_stl_multilingual_disease") model = AutoModelForTokenClassification.from_pretrained("BSC-NLP4BIA/DT4H_XLM-R_stl_multilingual_disease", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -45,7 +45,7 @@ This **multilingual clinical Named Entity Recognition (NER)** model is designed
|
|
| 45 |
- English (`en`)
|
| 46 |
- Dutch (`nl`)
|
| 47 |
- Swedish (`sv`)
|
| 48 |
-
- Czech (`
|
| 49 |
- **Base model:** `xlm-roberta-base`
|
| 50 |
- **Task:** Token classification (NER)
|
| 51 |
- **Label scheme:** BIO
|
|
@@ -89,8 +89,8 @@ To facilitate this process, we provide an inference script in a [GitHub reposito
|
|
| 89 |
- Exports predictions as a TSV file in the format required for the [MultiClinAI evaluation library](https://github.com/nlp4bia-bsc/MultiClinAIEval):
|
| 90 |
|
| 91 |
```text
|
| 92 |
-
filename
|
| 93 |
-
MultiClinNER-en-test-disease-00019
|
| 94 |
```
|
| 95 |
|
| 96 |
## Limitations and bias
|
|
|
|
| 45 |
- English (`en`)
|
| 46 |
- Dutch (`nl`)
|
| 47 |
- Swedish (`sv`)
|
| 48 |
+
- Czech (`cs`)
|
| 49 |
- **Base model:** `xlm-roberta-base`
|
| 50 |
- **Task:** Token classification (NER)
|
| 51 |
- **Label scheme:** BIO
|
|
|
|
| 89 |
- Exports predictions as a TSV file in the format required for the [MultiClinAI evaluation library](https://github.com/nlp4bia-bsc/MultiClinAIEval):
|
| 90 |
|
| 91 |
```text
|
| 92 |
+
filename label start_span end_span text
|
| 93 |
+
MultiClinNER-en-test-disease-00019 DISEASE 154 165 myocarditis
|
| 94 |
```
|
| 95 |
|
| 96 |
## Limitations and bias
|