Syntactically Guided Neural Machine Translation
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
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.
Description
Keywords
cs.CL, cs.CL
Journal Title
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics
Conference Name
Journal ISSN
Volume Title
2
Publisher
Association for Computational Linguistics
Publisher DOI
Sponsorship
Engineering and Physical Sciences Research Council (EP/L027623/1)
Engineering and Physical Sciences Research Council (Grant ID: EP/L027623/1)