Zero-Shot classification with Transformers
Classify text into arbitrary labels with a zero-shot classification pipeline.
1 min read
Updated
Zero-shot classification lets you label text with categories the model was never explicitly trained on. This script loads a multilingual NLI model and classifies text against arbitrary labels. The script is below.
zero-shot-classification.py
python
from transformers import pipeline
classifier = pipeline("zero-shot-classification",
model="BaptisteDoyen/camembert-base-xnli")
sequence = "L'équipe de France joue aujourd'hui au Parc des Princes"
candidate_labels = ["sport","politique","science"]
hypothesis_template = "Ce texte parle de {}."
result = classifier(sequence, candidate_labels, hypothesis_template=hypothesis_template)
print(result)