Ofir Press
Ofir Press
Verified email at cs.washington.edu - Homepage
TitleCited byYear
Using the Output Embedding to Improve Language Models
O Press, L Wolf
EACL 2017, 2017
Language Generation with Recurrent Generative Adversarial Networks without Pre-training
O Press, A Bar, B Bogin, J Berant, L Wolf
1st Workshop on Learning to Generate Natural Language at ICML 2017, 2017
You May Not Need Attention
O Press, NA Smith
arXiv preprint arXiv:1810.13409, 2018
Partially Shuffling the Training Data to Improve Language Models
O Press
arXiv preprint arXiv:1903.04167, 2019
Improving Transformer Models by Reordering their Sublayers
O Press, NA Smith, O Levy
arXiv preprint arXiv:1911.03864, 2019
The system can't perform the operation now. Try again later.
Articles 1–5