metadata
license: unknown
datasets:
- PolyAI/minds14
language:
- en
metrics:
- accuracy
- precision
- recall
- f1
base_model:
- FacebookAI/roberta-base
pipeline_tag: text-classification
model-index:
- name: roBERTa-minds14-en-classifier
results:
- task:
type: text-classification
dataset:
name: minds-14
type: en
metrics:
- name: Accuracy
type: Accuracy
value: 0.9724
- task:
type: text-classification
dataset:
name: minds-14
type: en
metrics:
- name: Precision
type: Precision
value: 0.9736
- task:
type: text-classification
dataset:
name: minds-14
type: en
metrics:
- name: Recall
type: Recall
value: 0.9724
- task:
type: text-classification
dataset:
name: minds-14
type: en
metrics:
- name: f1
type: f1
value: 0.9724
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}]