Created
April 16, 2020 22:59
-
-
Save thiagomarzagao/77e641fe347fabcb5bd46111ec3316fe to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch | |
from transformers import AutoTokenizer, AutoModelForTokenClassification | |
tokenizer = AutoTokenizer.from_pretrained('neuralmind/bert-large-portuguese-cased') | |
model = AutoModelForTokenClassification.from_pretrained('neuralmind/bert-large-portuguese-cased') | |
label_list = [ | |
'O', # outside of a named entity | |
'B-MISC', # beginning of a miscellaneous entity right after another miscellaneous entity | |
'I-MISC', # miscellaneous entity | |
'B-PER', # beginning of a person's name right after another person's name | |
'I-PER', # person's name | |
'B-ORG', # beginning of a location right after another location | |
'I-LOC' # location | |
] | |
text = 'Luiz Henrique Mandetta (Campo Grande, 30 de novembro de 1964) é um médico ortopedista e político brasileiro. Foi deputado federal e atualmente é Ministro da Saúde no governo de Jair Bolsonaro.' | |
tokens = tokenizer.tokenize(tokenizer.decode(tokenizer.encode(text))) | |
inputs = tokenizer.encode(text, return_tensors = 'pt') | |
outputs = model(inputs)[0] | |
predictions = torch.argmax(outputs, dim = 2) | |
print([(token, label_list[prediction]) for token, prediction in zip(tokens, predictions[0].tolist())]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment