Treating lexical constraints as soft external memories lets an NMT model correct noisy user hints and benefit from automatically generated hints, improving BLEU over hard constrained decoding.
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
-
Neural Machine Translation with Noisy Lexical Constraints
Treating lexical constraints as soft external memories lets an NMT model correct noisy user hints and benefit from automatically generated hints, improving BLEU over hard constrained decoding.