New paper! We perform a systematic study of transfer learning for NLP using a unified text-to-text model, then push the limits to achieve SoTA on GLUE, SuperGLUE, CNN/DM, and SQuAD. Paper: arxiv.org/abs/1910.10683 Code/models/data/etc: git.io/Je0cZ S

Sören Mindermann @sorenmind · Oct 24, 2019

Great thread & paper about NLP transfer learning!

Tweet Oct 24, 2019

by Colin Raffel

Recommended by 1 person

1 mention