Text Classification
sentence-transformers
PyTorch
Spanish
roberta
bert
biomedical
lexical semantics
bionlp
Instructions to use BSC-NLP4BIA/biomedical-term-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use BSC-NLP4BIA/biomedical-term-classifier with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BSC-NLP4BIA/biomedical-term-classifier") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -57,12 +57,12 @@ Mediante biopsia se diagnostica adenocarcinoma de pr贸stata Gleason 4+4=8 con me
|
|
| 57 |
Se trata con 脕cido Zoledr贸nico 4 mg iv/4 semanas.
|
| 58 |
"""
|
| 59 |
termextractor(text)
|
| 60 |
-
# You can also access the class storing the
|
| 61 |
categorizer = termextractor.categorizer
|
| 62 |
```
|
| 63 |
|
| 64 |
## Training
|
| 65 |
-
The model has been trained using data obtained from NER Gold Standard Corpora also generated by BSC-NLP4BIA, including [MedProcNER](https://temu.bsc.es/medprocner/), [DISTEMIST](https://temu.bsc.es/distemist/), [SympTEMIST](https://temu.bsc.es/symptemist/), [CANTEMIST](https://temu.bsc.es/cantemist/), and [PharmaCoNER](https://temu.bsc.es/pharmaconer/), among others.
|
| 66 |
|
| 67 |
## Evaluation
|
| 68 |
To be published
|
|
|
|
| 57 |
Se trata con 脕cido Zoledr贸nico 4 mg iv/4 semanas.
|
| 58 |
"""
|
| 59 |
termextractor(text)
|
| 60 |
+
# You can also access the class storing the Transformer model
|
| 61 |
categorizer = termextractor.categorizer
|
| 62 |
```
|
| 63 |
|
| 64 |
## Training
|
| 65 |
+
The used pre-trained model is SapBERT-from-roberta-base-biomedical-clinical-es from the BSC-NLP4BIA reserch group. The model has been trained using data obtained from NER Gold Standard Corpora also generated by BSC-NLP4BIA, including [MedProcNER](https://temu.bsc.es/medprocner/), [DISTEMIST](https://temu.bsc.es/distemist/), [SympTEMIST](https://temu.bsc.es/symptemist/), [CANTEMIST](https://temu.bsc.es/cantemist/), and [PharmaCoNER](https://temu.bsc.es/pharmaconer/), among others.
|
| 66 |
|
| 67 |
## Evaluation
|
| 68 |
To be published
|