566 citations · 667 across the 12 of their papers we have counts for
3 papers · 1 filter
Taming Sparsely Activated Transformer with Stochastic Experts
Simiao Zuo, Xiaodong Liu, Jian Jiao +5
Sparsely activated models (SAMs), such as Mixture-of-Experts (MoE), can easily scale to have outrageously large amounts of parameters without significant increase in computational…
Improving Multilingual Translation by Representation and Gradient Regularization
Yilin Yang, Akiko Eriguchi, Alexandre Muzio +3
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Des…
Discovering Representation Sprachbund For Multilingual Pre-Training
Yimin Fan, Yaobo Liang, Alexandre Muzio +4
Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low…