A noisy top-k gated mixture-of-experts layer between LSTMs scales neural networks to 137B parameters with sub-linear compute, beating SOTA on language modeling and machine translation.
citation dossier
NMT before RL
3Pith papers citing it
3reference links
cs.CLtop field · 2 papers
ACCEPTtop verdict bucket · 2 papers
why this work matters in Pith
Pith has found this work in 3 reviewed papers. Its strongest current cluster is cs.CL (2 papers). The largest review-status bucket among citing papers is ACCEPT (2 papers). For highly cited works, this page shows a dossier first and a bounded explorer second; it never tries to render every citing paper at once.
representative citing papers
GNMT deploys 8-layer LSTMs with attention, wordpieces, low-precision inference, and coverage-penalized beam search to match state-of-the-art on WMT'14 En-Fr and En-De while cutting translation errors by 60% in human evaluations.
Pith review generated a malformed one-line summary.
citing papers explorer
-
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
A noisy top-k gated mixture-of-experts layer between LSTMs scales neural networks to 137B parameters with sub-linear compute, beating SOTA on language modeling and machine translation.
-
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
GNMT deploys 8-layer LSTMs with attention, wordpieces, low-precision inference, and coverage-penalized beam search to match state-of-the-art on WMT'14 En-Fr and En-De while cutting translation errors by 60% in human evaluations.
-
Attention Is All You Need
Pith review generated a malformed one-line summary.