|
--- |
|
language: "pt" |
|
widget: |
|
- text: "O paciente recebeu no hospital e falou com a médica" |
|
- text: "COMO ESQUEMA DE MEDICAÇÃO PARA ICC PRESCRITO NO ALTA, RECEBE FUROSEMIDA 40 BID, ISOSSORBIDA 40 TID, DIGOXINA 0,25 /D, CAPTOPRIL 50 TID E ESPIRONOLACTONA 25 /D." |
|
- text: "ESTAVA EM USO DE FUROSEMIDA 40 BID, DIGOXINA 0,25 /D, SINVASTATINA 40 /NOITE, CAPTOPRIL 50 TID, ISOSSORBIDA 20 TID, AAS 100 /D E ESPIRONOLACTONA 25 /D." |
|
datasets: |
|
- MacMorpho |
|
--- |
|
|
|
# POS-Tagger Bio Portuguese |
|
|
|
We fine-tuned the BioBERTpt(all) model with the MacMorpho corpus for the Post-Tagger task, with 10 epochs, achieving a general F1-Score of 0.9814. |
|
|
|
Metrics: |
|
|
|
``` |
|
Precision Recall F1 Suport |
|
accuracy 0.98 38320 |
|
macro avg 0.95 0.92 0.93 38320 |
|
weighted avg 0.98 0.98 0.98 38320 |
|
|
|
F1: 0.981447444144733 Accuracy: 0.9815240083507307 |
|
``` |
|
|
|
## Acknowledgements |
|
|
|
This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001. |
|
|
|
## Citation |
|
``` |
|
coming soon |
|
``` |
|
|
|
## Questions? |
|
|
|
Please, post a Github issue on the [NLP Portuguese Chunking](https://github.com/HAILab-PUCPR/nlp-portuguese-chunking). |
|
|
|
|
