@inproceedings{quinn-ballesteros-2018-pieces,
title = "Pieces of Eight: 8-bit Neural Machine Translation",
author = "Quinn, Jerry and
Ballesteros, Miguel",
editor = "Bangalore, Srinivas and
Chu-Carroll, Jennifer and
Li, Yunyao",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)",
month = jun,
year = "2018",
address = "New Orleans - Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-3014/",
doi = "10.18653/v1/N18-3014",
pages = "114--120",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="quinn-ballesteros-2018-pieces">
<titleInfo>
<title>Pieces of Eight: 8-bit Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jerry</namePart>
<namePart type="family">Quinn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Ballesteros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srinivas</namePart>
<namePart type="family">Bangalore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Chu-Carroll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans - Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">quinn-ballesteros-2018-pieces</identifier>
<identifier type="doi">10.18653/v1/N18-3014</identifier>
<location>
<url>https://aclanthology.org/N18-3014/</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>114</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pieces of Eight: 8-bit Neural Machine Translation
%A Quinn, Jerry
%A Ballesteros, Miguel
%Y Bangalore, Srinivas
%Y Chu-Carroll, Jennifer
%Y Li, Yunyao
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans - Louisiana
%F quinn-ballesteros-2018-pieces
%X 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.
%R 10.18653/v1/N18-3014
%U https://aclanthology.org/N18-3014/
%U https://doi.org/10.18653/v1/N18-3014
%P 114-120
Markdown (Informal)
[Pieces of Eight: 8-bit Neural Machine Translation](https://aclanthology.org/N18-3014/) (Quinn & Ballesteros, NAACL 2018)
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.