MoE

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Machine TranslationonWMT2014 English-French
BLEU score· 2017-01-23
40.56
best: 46.4 (Transformer+BT (ADMIN init))
SOTA
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer arXiv:1701.06538
Machine TranslationonWMT2014 English-German
BLEU score· 2017-01-23
26.03
best: 35.14 (Transformer Cycle (Rev))
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer arXiv:1701.06538