Affordable Access

Syntactically Guided Neural Machine Translation

Authors
  • Stahlberg, Felix
  • Hasler, Eva
  • Waite, Aurelien
  • Byrne, Bill
Type
Preprint
Publication Date
May 19, 2016
Submission Date
May 15, 2016
Identifiers
arXiv ID: 1605.04569
Source
arXiv
License
Yellow
External links

Abstract

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.

Report this publication

Statistics

Seen <100 times