---
language: "pt"
widget:
- text: "O paciente recebeu [MASK] do hospital."
- text: "O médico receitou a medicação para controlar a [MASK]."
- text: "O principal [MASK] da COVID-19 é tosse seca."
- text: "O vírus da gripe apresenta um [MASK] constituído por segmentos de ácido ribonucleico."

datasets: 
- biomedical literature from Scielo and Pubmed
thumbnail: "https://raw.githubusercontent.com/HAILab-PUCPR/BioBERTpt/master/images/logo-biobertpr1.png"
---

<img src="https://raw.githubusercontent.com/HAILab-PUCPR/BioBERTpt/master/images/logo-biobertpr1.png" alt="Logo BioBERTpt">

# BioBERTpt - Portuguese Clinical and Biomedical BERT

The [BioBERTpt - A Portuguese Neural Language Model for Clinical Named Entity Recognition](https://www.aclweb.org/anthology/2020.clinicalnlp-1.7/) paper contains clinical and biomedical BERT-based models for Portuguese Language, initialized with BERT-Multilingual-Cased & trained on clinical notes and biomedical literature. 

This model card describes the BioBERTpt(all) model, a full version with clinical narratives and biomedical literature in Portuguese language. 

## How to use the model

Load the model via the transformers library:
```
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("pucpr/biobertpt-all")
model = AutoModel.from_pretrained("pucpr/biobertpt-all")
```

## More Information

Refer to the original paper, [BioBERTpt - A Portuguese Neural Language Model for Clinical Named Entity Recognition](https://www.aclweb.org/anthology/2020.clinicalnlp-1.7/) for additional details and performance on Portuguese NER tasks.

## Questions?

Post a Github issue on the [BioBERTpt repo](https://github.com/HAILab-PUCPR/BioBERTpt).