Token Classification
Transformers
PyTorch
roberta
LABEL-0 = NONE
LABEL-1 = B-DATE
LABEL-2 = I-DATE
LABEL-3 = B-TIME
LABEL-4 = I-TIME
LABEL-5 = B-DURATION
LABEL-6 = I-DURATION
LABEL-7 = B-SET
LABEL-8 = I-SET
Instructions to use asdc/Bio-RoBERTime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use asdc/Bio-RoBERTime with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="asdc/Bio-RoBERTime")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("asdc/Bio-RoBERTime") model = AutoModelForTokenClassification.from_pretrained("asdc/Bio-RoBERTime", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -33,12 +33,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
# Bio-RoBERTime
|
| 34 |
|
| 35 |
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-biomedical-clinical-es](https://huggingface.co/PlanTL-GOB-ES/roberta-base-biomedical-clinical-es) on the None dataset.
|
| 36 |
-
|
| 37 |
-
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
-
|
| 41 |
-
|
|
|
|
|
|
|
| 42 |
|
| 43 |
## Model description
|
| 44 |
|
|
@@ -50,7 +52,7 @@ More information needed
|
|
| 50 |
|
| 51 |
## Training and evaluation data
|
| 52 |
|
| 53 |
-
|
| 54 |
|
| 55 |
## Training procedure
|
| 56 |
|
|
|
|
| 33 |
# Bio-RoBERTime
|
| 34 |
|
| 35 |
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-biomedical-clinical-es](https://huggingface.co/PlanTL-GOB-ES/roberta-base-biomedical-clinical-es) on the None dataset.
|
| 36 |
+
|
| 37 |
+
It achieves the following results on the E3C test set following the TempEval-3 evaluation metrics:
|
| 38 |
+
|
| 39 |
+
| E3C | Strict | Relaxed | type |
|
| 40 |
+
|------------|:-------:|--------:|-------:|
|
| 41 |
+
| RoBERTime | 0.7606 | 0.9108 | 0.8357 |
|
| 42 |
+
| Heideltime | 0.5945 | 0.7558 | 0.6083 |
|
| 43 |
+
| Annotador | 0.6006 | 0.7347 | 0.5598 |
|
| 44 |
|
| 45 |
## Model description
|
| 46 |
|
|
|
|
| 52 |
|
| 53 |
## Training and evaluation data
|
| 54 |
|
| 55 |
+
This model has been trained on the Spanish Timebank corpus and E3C corpus
|
| 56 |
|
| 57 |
## Training procedure
|
| 58 |
|