Instructions to use psybertpt/psyBERTpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use psybertpt/psyBERTpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="psybertpt/psyBERTpt")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("psybertpt/psyBERTpt") model = AutoModelForTokenClassification.from_pretrained("psybertpt/psyBERTpt") - Notebooks
- Google Colab
- Kaggle
Portuguese Clinical NER - Psychiatric Specialized
This model is the first clinical psychiatric specialized model for the portuguese language. We annotated 9 categories from admission notes of an emergency specialized hospital of psychiatry in Brazil. The article: PsyBERTpt: A Clinical Entity Recognition Model for Psychiatric Narratives, is waiting to be published.
NER Categories:
- Self-Destructive Behavior
- Diagnosis
- Drug
- Pharmaceutical
- Psychic Function
- Family History
- Patient History
- Observation
- Symptom and Psychological Complaint
Acknowledgements
this model can only be developed thanks to the fantastic work of committed people, who are part of the following institutions:
- Universidade Estadual Paulista Júlio de Mesquita Filho - UNESP
- Faculdade de Medicina de São José do Rio Preto - FAMERP
- Pontífica Universidade Católica do Paraná - PUCPR
- Hospital Dr. Adolfo Bezerra de Menezes - HABM
Citation
Waiting to be published
Questions?
Post a Github issue on the psyBERTpt repo.
- Downloads last month
- 6