Pieces of Eight: 8-bit Neural Machine Translation

Jerry Quinn, Miguel Ballesteros


Abstract
Neural machine translation has achieved levels of fluency and adequacy that would have been surprising a short time ago. Output quality is extremely relevant for industry purposes, however it is equally important to produce results in the shortest time possible, mainly for latency-sensitive applications and to control cloud hosting costs. In this paper we show the effectiveness of translating with 8-bit quantization for models that have been trained using 32-bit floating point values. Results show that 8-bit translation makes a non-negligible impact in terms of speed with no degradation in accuracy and adequacy.
Anthology ID:
N18-3014
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:
114–120
Language:
URL:
https://aclanthology.org/N18-3014
DOI:
10.18653/v1/N18-3014
Bibkey:
Cite (ACL):
Jerry Quinn and Miguel Ballesteros. 2018. Pieces of Eight: 8-bit Neural Machine Translation. 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 114–120, New Orleans - Louisiana. Association for Computational Linguistics.
Cite (Informal):
Pieces of Eight: 8-bit Neural Machine Translation (Quinn & Ballesteros, NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-3014.pdf
Video:
 https://aclanthology.org/N18-3014.mp4