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.
Bidirectional recurrent neural networks.IEEE Transactions on Signal Processing 45, 11 (Nov
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2016 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
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.