Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment

Gonzalo Iglesias, William Tambellini, Adrià De Gispert, Eva Hasler, Bill Byrne


Abstract
We describe a batched beam decoding algorithm for NMT with LMBR n-gram posteriors, showing that LMBR techniques still yield gains on top of the best recently reported results with Transformers. We also discuss acceleration strategies for deployment, and the effect of the beam size and batching on memory and speed.
Anthology ID:
N18-3013
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)
Month:
June
Year:
2018
Address:
New Orleans - Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
106–113
URL:
https://www.aclweb.org/anthology/N18-3013
DOI:
10.18653/v1/N18-3013
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/N18-3013.pdf
Video:
 http://vimeo.com/277631374