Commit
•
ab0f578
1
Parent(s):
9f3c228
Update README.md
Browse files
README.md
CHANGED
|
@@ -52,6 +52,8 @@ language:
|
|
| 52 |
|
| 53 |
This is a multilingual clinical NER model extracting DRUG, STRENGTH, FREQUENCY, DURATION, DOSAGE and FORM entities from a medical text.
|
| 54 |
|
|
|
|
|
|
|
| 55 |
## Evaluation Metrics on [MedNERF dataset](https://huggingface.co/datasets/Posos/MedNERF)
|
| 56 |
|
| 57 |
- Loss: 0.692
|
|
|
|
| 52 |
|
| 53 |
This is a multilingual clinical NER model extracting DRUG, STRENGTH, FREQUENCY, DURATION, DOSAGE and FORM entities from a medical text.
|
| 54 |
|
| 55 |
+
It consist of XLM-R Base fine-tuned on n2c2 (English). It is the model that obtains the best results on our French evaluation test set [MedNERF](https://huggingface.co/datasets/Posos/MedNERF) in a zero-shot cross-lingual transfer setting.
|
| 56 |
+
|
| 57 |
## Evaluation Metrics on [MedNERF dataset](https://huggingface.co/datasets/Posos/MedNERF)
|
| 58 |
|
| 59 |
- Loss: 0.692
|