Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices

Understand

We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT).

• Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT.
• The NMT score is combined with the Bayes-risk of the translation according the SMT lattice.
• This makes our approach much more flexible than $n$-best list or lattice rescoring as the neural decoder is not restricted to the SMT search space.