A standard sequence-to-sequence model used as a noisy channel model improves NMT by up to 3.2 BLEU over a direct model across four language pairs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Simple and Effective Noisy Channel Modeling for Neural Machine Translation
A standard sequence-to-sequence model used as a noisy channel model improves NMT by up to 3.2 BLEU over a direct model across four language pairs.