Re:T0* – Series of encoder-decoder models trained on a large...
by srush on Monday October 18, 2021 @12:02PM
(#28906969)
Yes, this is an important challenge. There has been a lot of interest in the NLP community right now, particularly around QA tasks [1] Standard supervised models do it well, but zero-shot models still have trouble.
1. https://arxiv.org/abs/1806.03822