Syntactically Guided Neural Machine Translation

05/15/2016
by   Felix Stahlberg, et al.
0

We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural machine translation (NMT). Weight pushing transforms the Hiero scores for complete translation hypotheses, with the full translation grammar score and full n-gram language model score, into posteriors compatible with NMT predictive probabilities. With a slightly modified NMT beam-search decoder we find gains over both Hiero and NMT decoding alone, with practical advantages in extending NMT to very large input and output vocabularies.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset