Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 4 Next »

Zero-shot learning refers to the model’s ability to classify objects that it has never seen before, or in other words,  allow us to assign an appropriate label to a piece of text without having received any training examples before.

The Zero-shot models have multiple advantages, including:

No need to be fine-tuned. Zero-shot models are one of the fastest ways to classify text without taking up your time for additional annotation of examples.

Unlimited possibilities for labels.  As in general zero-shot models work without any training data from you, your model will be able to detect any label you might be interested in finding in your data, such as emotions, different topics, sentiment, personality traits and others.

High-performance quality. Zero-shot models allow rapid classification of the data set without the need for prior training while getting results similar to those of a deep learning model trained with large amounts of data.


Next: How to use Zero-shot API?

  • No labels