Adding context gates with PMI-based regularization to Transformer decoder layers yields an average +1.0 BLEU across four translation tasks.
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
-
Regularized Context Gates on Transformer for Machine Translation
Adding context gates with PMI-based regularization to Transformer decoder layers yields an average +1.0 BLEU across four translation tasks.