The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020

We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, distributed mixed precision training, and effici...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Domhan, Tobias, Denkowski, Michael, Vilar, David, Niu, Xing, Hieber, Felix, Heafield, Kenneth
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.08.2020
Subjects
Decoding
Gluons
Machine translation
Modernization
Toolkits
Training
Online AccessGet full text

Cover

Abstract We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, distributed mixed precision training, and efficient CPU decoding with 8-bit quantization. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.
AbstractList We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, distributed mixed precision training, and efficient CPU decoding with 8-bit quantization. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.
Author Vilar, David
Domhan, Tobias
Hieber, Felix
Niu, Xing
Denkowski, Michael
Heafield, Kenneth
Author_xml – sequence: 1
  givenname: Tobias
  surname: Domhan
  fullname: Domhan, Tobias
– sequence: 2
  givenname: Michael
  surname: Denkowski
  fullname: Denkowski, Michael
– sequence: 3
  givenname: David
  surname: Vilar
  fullname: Vilar, David
– sequence: 4
  givenname: Xing
  surname: Niu
  fullname: Niu, Xing
– sequence: 5
  givenname: Felix
  surname: Hieber
  fullname: Hieber, Felix
– sequence: 6
  givenname: Kenneth
  surname: Heafield
  fullname: Heafield, Kenneth
BookMark eNqNyrsKwjAUgOEgCtbadzjgXEhPelsciigudTF7CeVILyHRJB18ex18AKd_-P4dWxtraMUiFCJL6xxxyxLvJ845lhUWhYjYUQ4Ed9vP9CZAuNHilIZW9cNoCKRTxmsVRmtAWqvnMYAK0LSyAeTI92zzUNpT8mvMDpezPF3Tp7OvhXzoJrs486UOcyF4WVdVJv67PsGQN2U
ContentType Paper
Copyright 2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 8FE
8FG
ABJCF
ABUWG
AFKRA
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
L6V
M7S
PIMPY
PQEST
PQQKQ
PQUKI
PRINS
PTHSS
DatabaseName ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central
ProQuest Central Essentials
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central
SciTech Premium Collection (Proquest) (PQ_SDU_P3)
ProQuest Engineering Collection
ProQuest Engineering Database
Publicly Available Content Database
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
DatabaseTitle Publicly Available Content Database
Engineering Database
Technology Collection
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
ProQuest Engineering Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
Materials Science & Engineering Collection
ProQuest One Academic
Engineering Collection
DatabaseTitleList Publicly Available Content Database
Database_xml – sequence: 1
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 2331-8422
Genre Working Paper/Pre-Print
GroupedDBID 8FE
8FG
ABJCF
ABUWG
AFKRA
ALMA_UNASSIGNED_HOLDINGS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FRJ
HCIFZ
L6V
M7S
M~E
PIMPY
PQEST
PQQKQ
PQUKI
PRINS
PTHSS
ID FETCH-proquest_journals_24330687713
IEDL.DBID BENPR
IngestDate Thu Oct 10 17:15:29 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-proquest_journals_24330687713
OpenAccessLink https://www.proquest.com/docview/2433068771?pq-origsite=%requestingapplication%
PQID 2433068771
PQPubID 2050157
ParticipantIDs proquest_journals_2433068771
PublicationCentury 2000
PublicationDate 20200811
PublicationDateYYYYMMDD 2020-08-11
PublicationDate_xml – month: 08
  year: 2020
  text: 20200811
  day: 11
PublicationDecade 2020
PublicationPlace Ithaca
PublicationPlace_xml – name: Ithaca
PublicationTitle arXiv.org
PublicationYear 2020
Publisher Cornell University Library, arXiv.org
Publisher_xml – name: Cornell University Library, arXiv.org
SSID ssj0002672553
Score 3.2797022
SecondaryResourceType preprint
Snippet We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base...
SourceID proquest
SourceType Aggregation Database
SubjectTerms Decoding
Gluons
Machine translation
Modernization
Toolkits
Training
Title The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
URI https://www.proquest.com/docview/2433068771
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEB7sLoI3n_ioJaDXoMlmk-xJquxahC1FV-itxCQFsbi1u1797SZxqwehxxDIi8nMfF8-MgCXdu7_ZNcKG2USzNI0wZkxXiYmJUmFcUYUVL5jPnpmD9N02hFuTSerXPvE4KhNrT1HfkWZQ95cCkFulh_YV43yr6tdCY0exNQhhesI4tt8PHn8ZVkoFy5nTv452hA9il2IJ2ppV3uwZd_3YTuILnVzEEq8o6fa3yOLKPL_ZKgFKoO80aIQRX6Uaqiq68Xba4tUi4ZlNUTUpV-HcFHk1d0Ir-ecdXbRzP52kRxB5AC-PQZE5hnjzGaZdliLWyE50VRJlShlpUrZCfQ3jXS6ufsMdvyiPA9KSB-idvVpz10gbV8G0JPF_aA7M9cqv_Jv_Vl6_A
link.rule.ids 783,787,12777,21400,33385,33756,43612,43817
linkProvider ProQuest
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bS8MwFD7oirg3r3iZGtDXIGnTNH2SKRtV1zK0wt5KTDKQDTvX7v-bxEwfhD0HcuPknPN9-TgH4EZPbU12KbASKsI0jiOcKmVlYpyTOFHGiJzKt2DZG32axBNPuDVeVrn2ic5Rq1pajvw2pAZ5M54k5G7xhW3XKPu76ltobENgS1UZ8BXcD4rxyy_LErLE5MzRP0frosdwD4KxWOjlPmzpzwPYcaJL2Ry6Fu_otbbvSKMQ2ToZYo5yJ2_UyEWRH6UaKut6PvtokWhRPy_7KDTp1xFcDwflQ4bXa1beLprq7xTRMXQMwNcngMg0pYzqNJUGazGdcEZkKLiIhNBcxPQUeptmOts8fAW7WZmPqtFj8XwOXbtBy4kS0oNOu1zpCxNU2_dLf3PfKPZ73w
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=The+Sockeye+2+Neural+Machine+Translation+Toolkit+at+AMTA+2020&rft.jtitle=arXiv.org&rft.au=Domhan%2C+Tobias&rft.au=Denkowski%2C+Michael&rft.au=Vilar%2C+David&rft.au=Niu%2C+Xing&rft.date=2020-08-11&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422