Zero shot text classification is the most underrated and useful task for various NLP tasks 
These models can predict what a given text is about without explicitly being trained on the classes 
You can use these models off the shelf for topic classification or sentiment analysis, or even use it for labelling! 
Learn more here 
https://huggingface.co/tasks/zero-shot-classification
@mervenoyan@sigmoid.socialSee below how to use zero shot classification models with few lines of code 
@mervenoyan lol, I saw this second tweet first and was going to say zero-shot classification is so underrated. Completely agree. You can accomplish so much with it, especially when chaining it together with other zero-shot classification or Q&A models, etc.
@kbaxter if I was left on a deserted island and had to pick a model it would be this zero shot BART model for sure 
@mervenoyan gotta check this out. this sounds brilliant. they also use textual entailment, fine-tuned to predict entailment relation of 3 million wikipedia articles with their categories.