A shorter reply would be: It would be great to compare PET not only to GPT-3, but also to other models, especially ones geared towards few-shot learning.
Do you know of any other models that should be used for such a comparison, or are there already any relevant results on SuperGLUE that should be mentioned?
Do you know of any other models that should be used for such a comparison, or are there already any relevant results on SuperGLUE that should be mentioned?