this model based on roberta model that trained with minds-14 dataset, only trained in english version : enUS + enAU + enGB
the intent_classes available:
intent_classes = {
0: 'abroad',
1: 'address',
2: 'app_error',
3: 'atm_limit',
4: 'balance',
5: 'business_loan',
6: 'card_issues',
7: 'cash_deposit',
8: 'direct_debit',
9: 'freeze',
10: 'high_value_payment',
11: 'joint_account',
12: 'latest_transactions',
13: 'pay_bill'
}
example of using model to classify intent:
>>> from transformers import pipeline
model = "/content/RoBERTa-mind14-classifier-intent"
classifier = pipeline("text-classification", model=model)
text = "hi what's the maximum amount of money I can withdraw from" # Replace with your desired input text
prediction = classifier(text)
prediction
example output:
[{'label': 'LABEL_3', 'score': 0.9933607578277588}]
- Downloads last month
- 52
Model tree for kairaamilanii/RoBERTa-minds14-en
Base model
FacebookAI/roberta-baseDataset used to train kairaamilanii/RoBERTa-minds14-en
Space using kairaamilanii/RoBERTa-minds14-en 1
Evaluation results
- Accuracy on minds-14self-reported0.972
- Precision on minds-14self-reported0.974
- Recall on minds-14self-reported0.972
- f1 on minds-14self-reported0.972