An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
Paper • 1909.02027 • Published
How to use marice/bert-base-uncased-finetuned-clinc with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="marice/bert-base-uncased-finetuned-clinc") # Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("marice/bert-base-uncased-finetuned-clinc")
model = AutoModelForSequenceClassification.from_pretrained("marice/bert-base-uncased-finetuned-clinc")This model was trained on the CLINC150 dataset for customer intent detection. The dataset can be found on the Hub. The model is used in Chapter 8: Making Transformers Efficient in Production in the NLP with Transformers book. You can find the full code in the accompanying Github repository.