@inproceedings{klein-etal-2020-efficient,
title = "Efficient and High-Quality Neural Machine Translation with {O}pen{NMT}",
author = "Klein, Guillaume and
Zhang, Dakun and
Chouteau, Cl{\'e}ment and
Crego, Josep and
Senellart, Jean",
editor = "Birch, Alexandra and
Finch, Andrew and
Hayashi, Hiroaki and
Heafield, Kenneth and
Junczys-Dowmunt, Marcin and
Konstas, Ioannis and
Li, Xian and
Neubig, Graham and
Oda, Yusuke",
booktitle = "Proceedings of the Fourth Workshop on Neural Generation and Translation",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.ngt-1.25",
doi = "10.18653/v1/2020.ngt-1.25",
pages = "211--217",
abstract = "This paper describes the OpenNMT submissions to the WNGT 2020 efficiency shared task. We explore training and acceleration of Transformer models with various sizes that are trained in a teacher-student setup. We also present a custom and optimized C++ inference engine that enables fast CPU and GPU decoding with few dependencies. By combining additional optimizations and parallelization techniques, we create small, efficient, and high-quality neural machine translation models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klein-etal-2020-efficient">
<titleInfo>
<title>Efficient and High-Quality Neural Machine Translation with OpenNMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dakun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clément</namePart>
<namePart type="family">Chouteau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="family">Crego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Senellart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Neural Generation and Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Heafield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Junczys-Dowmunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the OpenNMT submissions to the WNGT 2020 efficiency shared task. We explore training and acceleration of Transformer models with various sizes that are trained in a teacher-student setup. We also present a custom and optimized C++ inference engine that enables fast CPU and GPU decoding with few dependencies. By combining additional optimizations and parallelization techniques, we create small, efficient, and high-quality neural machine translation models.</abstract>
<identifier type="citekey">klein-etal-2020-efficient</identifier>
<identifier type="doi">10.18653/v1/2020.ngt-1.25</identifier>
<location>
<url>https://aclanthology.org/2020.ngt-1.25</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>211</start>
<end>217</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient and High-Quality Neural Machine Translation with OpenNMT
%A Klein, Guillaume
%A Zhang, Dakun
%A Chouteau, Clément
%A Crego, Josep
%A Senellart, Jean
%Y Birch, Alexandra
%Y Finch, Andrew
%Y Hayashi, Hiroaki
%Y Heafield, Kenneth
%Y Junczys-Dowmunt, Marcin
%Y Konstas, Ioannis
%Y Li, Xian
%Y Neubig, Graham
%Y Oda, Yusuke
%S Proceedings of the Fourth Workshop on Neural Generation and Translation
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F klein-etal-2020-efficient
%X This paper describes the OpenNMT submissions to the WNGT 2020 efficiency shared task. We explore training and acceleration of Transformer models with various sizes that are trained in a teacher-student setup. We also present a custom and optimized C++ inference engine that enables fast CPU and GPU decoding with few dependencies. By combining additional optimizations and parallelization techniques, we create small, efficient, and high-quality neural machine translation models.
%R 10.18653/v1/2020.ngt-1.25
%U https://aclanthology.org/2020.ngt-1.25
%U https://doi.org/10.18653/v1/2020.ngt-1.25
%P 211-217
Markdown (Informal)
[Efficient and High-Quality Neural Machine Translation with OpenNMT](https://aclanthology.org/2020.ngt-1.25) (Klein et al., NGT 2020)
ACL