@inproceedings{hoang-etal-2018-fast,
title = "Fast Neural Machine Translation Implementation",
author = "Hoang, Hieu and
Dwojak, Tomasz and
Krislauks, Rihards and
Torregrosa, Daniel and
Heafield, Kenneth",
editor = "Birch, Alexandra and
Finch, Andrew and
Luong, Thang and
Neubig, Graham and
Oda, Yusuke",
booktitle = "Proceedings of the 2nd Workshop on Neural Machine Translation and Generation",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-2714",
doi = "10.18653/v1/W18-2714",
pages = "116--121",
abstract = "This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-etal-2018-fast">
<titleInfo>
<title>Fast Neural Machine Translation Implementation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hieu</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Dwojak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rihards</namePart>
<namePart type="family">Krislauks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Torregrosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Heafield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Neural Machine Translation and Generation</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">Thang</namePart>
<namePart type="family">Luong</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">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.</abstract>
<identifier type="citekey">hoang-etal-2018-fast</identifier>
<identifier type="doi">10.18653/v1/W18-2714</identifier>
<location>
<url>https://aclanthology.org/W18-2714</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>116</start>
<end>121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast Neural Machine Translation Implementation
%A Hoang, Hieu
%A Dwojak, Tomasz
%A Krislauks, Rihards
%A Torregrosa, Daniel
%A Heafield, Kenneth
%Y Birch, Alexandra
%Y Finch, Andrew
%Y Luong, Thang
%Y Neubig, Graham
%Y Oda, Yusuke
%S Proceedings of the 2nd Workshop on Neural Machine Translation and Generation
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F hoang-etal-2018-fast
%X This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.
%R 10.18653/v1/W18-2714
%U https://aclanthology.org/W18-2714
%U https://doi.org/10.18653/v1/W18-2714
%P 116-121
Markdown (Informal)
[Fast Neural Machine Translation Implementation](https://aclanthology.org/W18-2714) (Hoang et al., NGT 2018)
ACL
- Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa, and Kenneth Heafield. 2018. Fast Neural Machine Translation Implementation. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 116–121, Melbourne, Australia. Association for Computational Linguistics.