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
Editors:
Srinivas Bangalore, Jennifer Chu-Carroll, Yunyao Li
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
106–113
Language:
URL:
https://aclanthology.org/N18-3013
DOI:
10.18653/v1/N18-3013
Bibkey:
Cite (ACL):
Gonzalo Iglesias, William Tambellini, Adrià De Gispert, Eva Hasler, and Bill Byrne. 2018. Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers), pages 106–113, New Orleans - Louisiana. Association for Computational Linguistics.
Cite (Informal):
Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment (Iglesias et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-3013.pdf
Video:
 https://aclanthology.org/N18-3013.mp4