A Reference Network built on local coordinate coding gives NMT decoders a compressed global context from the training corpus and improves BLEU on Zh-En and En-De by roughly 1.3 to 2.7 points over strong baselines.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reference Network for Neural Machine Translation
A Reference Network built on local coordinate coding gives NMT decoders a compressed global context from the training corpus and improves BLEU on Zh-En and En-De by roughly 1.3 to 2.7 points over strong baselines.