@inproceedings{kuchaiev-etal-2018-openseq2seq,
title = "{O}pen{S}eq2{S}eq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models",
author = "Kuchaiev, Oleksii and
Ginsburg, Boris and
Gitman, Igor and
Lavrukhin, Vitaly and
Case, Carl and
Micikevicius, Paulius",
editor = "Park, Eunjeong L. and
Hagiwara, Masato and
Milajevs, Dmitrijs and
Tan, Liling",
booktitle = "Proceedings of Workshop for {NLP} Open Source Software ({NLP}-{OSS})",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-2507",
doi = "10.18653/v1/W18-2507",
pages = "41--46",
abstract = "We present OpenSeq2Seq {--} an open-source toolkit for training sequence-to-sequence models. The main goal of our toolkit is to allow researchers to most effectively explore different sequence-to-sequence architectures. The efficiency is achieved by fully supporting distributed and mixed-precision training. OpenSeq2Seq provides building blocks for training encoder-decoder models for neural machine translation and automatic speech recognition. We plan to extend it with other modalities in the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuchaiev-etal-2018-openseq2seq">
<titleInfo>
<title>OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleksii</namePart>
<namePart type="family">Kuchaiev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Ginsburg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Gitman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitaly</namePart>
<namePart type="family">Lavrukhin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Case</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paulius</namePart>
<namePart type="family">Micikevicius</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 Workshop for NLP Open Source Software (NLP-OSS)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunjeong</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Hagiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrijs</namePart>
<namePart type="family">Milajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</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>We present OpenSeq2Seq – an open-source toolkit for training sequence-to-sequence models. The main goal of our toolkit is to allow researchers to most effectively explore different sequence-to-sequence architectures. The efficiency is achieved by fully supporting distributed and mixed-precision training. OpenSeq2Seq provides building blocks for training encoder-decoder models for neural machine translation and automatic speech recognition. We plan to extend it with other modalities in the future.</abstract>
<identifier type="citekey">kuchaiev-etal-2018-openseq2seq</identifier>
<identifier type="doi">10.18653/v1/W18-2507</identifier>
<location>
<url>https://aclanthology.org/W18-2507</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>41</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models
%A Kuchaiev, Oleksii
%A Ginsburg, Boris
%A Gitman, Igor
%A Lavrukhin, Vitaly
%A Case, Carl
%A Micikevicius, Paulius
%Y Park, Eunjeong L.
%Y Hagiwara, Masato
%Y Milajevs, Dmitrijs
%Y Tan, Liling
%S Proceedings of Workshop for NLP Open Source Software (NLP-OSS)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F kuchaiev-etal-2018-openseq2seq
%X We present OpenSeq2Seq – an open-source toolkit for training sequence-to-sequence models. The main goal of our toolkit is to allow researchers to most effectively explore different sequence-to-sequence architectures. The efficiency is achieved by fully supporting distributed and mixed-precision training. OpenSeq2Seq provides building blocks for training encoder-decoder models for neural machine translation and automatic speech recognition. We plan to extend it with other modalities in the future.
%R 10.18653/v1/W18-2507
%U https://aclanthology.org/W18-2507
%U https://doi.org/10.18653/v1/W18-2507
%P 41-46
Markdown (Informal)
[OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models](https://aclanthology.org/W18-2507) (Kuchaiev et al., NLPOSS 2018)
ACL