The State of Transfer Learning in NLP
Sebastian Ruder
AUGUST 18, 2019
Later approaches then scaled these representations to sentences and documents ( Le and Mikolov, 2014 ; Conneau et al., This goes back to layer-wise training of early deep neural networks ( Hinton et al., Early approaches such as word2vec ( Mikolov et al., 2017 ; Peters et al., 2006 ; Bengio et al.,
Let's personalize your content