Survey of Low-Resource Machine Translation

We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in...

Full description

Saved in:
Bibliographic Details
Published in:Computational linguistics - Association for Computational Linguistics Vol. 48; no. 3; pp. 673 - 732
Main Authors: Haddow, Barry, Bawden, Rachel, Barone, Antonio Valerio Miceli, Helcl, Jindřich, Birch, Alexandra
Format: Journal Article
Language:English
Published: One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA MIT Press 01.09.2022
MIT Press Journals, The
Massachusetts Institute of Technology Press (MIT Press)
The MIT Press
Subjects:
Computation and Language
Computer Science
Languages
Machine translation
Polls & surveys
Training
Translation
ISSN:0891-2017, 1530-9312
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful translation models when very little translated training data is available. We present a summary of this topical research field and provide a description of the techniques evaluated by researchers in several recent shared tasks in low-resource MT.
AbstractList We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful translation models when very little translated training data is available. We present a summary of this topical research field and provide a description of the techniques evaluated by researchers in several recent shared tasks in low-resource MT.
Author Bawden, Rachel
Haddow, Barry
Birch, Alexandra
Barone, Antonio Valerio Miceli
Helcl, Jindřich
Author_xml – sequence: 1
  givenname: Barry
  surname: Haddow
  fullname: Haddow, Barry
  email: bhaddow@inf.ed.ac.uk
  organization: University of Edinburgh School of Informatics. bhaddow@inf.ed.ac.uk
– sequence: 2
  givenname: Rachel
  surname: Bawden
  fullname: Bawden, Rachel
  email: Rachel.bawden@inria.fr
  organization: Inria, France. Rachel.bawden@inria.fr
– sequence: 3
  givenname: Antonio Valerio Miceli
  surname: Barone
  fullname: Barone, Antonio Valerio Miceli
  organization: University of Edinburgh School of Informatics. amiceli@ed.ac.uk
– sequence: 4
  givenname: Jindřich
  surname: Helcl
  fullname: Helcl, Jindřich
  email: jhelcl@ed.ac.uk
  organization: University of Edinburgh School of Informatics. jhelcl@ed.ac.uk
– sequence: 5
  givenname: Alexandra
  surname: Birch
  fullname: Birch, Alexandra
  email: a.birch@ed.ac.uk
  organization: University of Edinburgh School of Informatics .a.birch@ed.ac.uk
BackLink https://inria.hal.science/hal-03479757$$DView record in HAL
BookMark eNp1kU1rFEEQhhuJ4Gb15g9Y8KLB0eqv6embIagJrAgaz0X1x5heJtNrz-xK_PXOZhQSMaeG4qmn36o6Zkd97iNjzzm84bwWb33uEhICKFU_YguuJVRWcnHEFtBYXgng5gk7HoYNABiQZsFOvu7KPt6scrta55_VlzjkXfFx9Yn8Verj6rJQP3Q0ptw_ZY9b6ob47M-7ZN8-vL88O6_Wnz9enJ2uK68sHystfKO8AkdBmzr6BpSuZWikd66h0BhpmgCBHBnJNbl6SgbOxthGrrULcskuZm_ItMFtSddUbjBTwttCLt-Ryph8F9HXJrZWUHRWqKiBbN1SIOlA2tBOHyzZq9l1Rd091fnpGg81kMpYo81eTuyLmd2W_GMXhxE30y76aVQUU8ZGKiEPRjFTvuRhKLFFn8bb_YyFUocc8HALvHuLqen1P01_szyAv5zx63QnxAPou_-gB2SvmiRRCsUFoAAhECwCx19pe1_xG8n3rq8
CitedBy_id crossref_primary_10_3389_fenvs_2025_1578634
crossref_primary_10_1145_3610773
crossref_primary_10_1109_ACCESS_2025_3559135
crossref_primary_10_26599_TST_2023_9010097
crossref_primary_10_1145_3625095
crossref_primary_10_3390_sym17071005
crossref_primary_10_1016_j_patter_2025_101313
crossref_primary_10_1109_ACCESS_2023_3336019
crossref_primary_10_1038_s42256_025_01096_6
crossref_primary_10_1542_peds_2023_065573
crossref_primary_10_1186_s12909_025_07452_9
crossref_primary_10_1093_llc_fqae089
crossref_primary_10_1145_3639930
crossref_primary_10_1177_14727978251366539
crossref_primary_10_3389_fmicb_2025_1634194
crossref_primary_10_1007_s40747_025_01780_5
crossref_primary_10_1093_jamia_ocaf150
crossref_primary_10_3390_info16090723
crossref_primary_10_3390_app15169039
crossref_primary_10_33889_IJMEMS_2024_9_5_056
crossref_primary_10_1109_ACCESS_2025_3570699
crossref_primary_10_25046_aj100204
crossref_primary_10_1016_j_ipm_2022_103245
crossref_primary_10_3390_informatics11040090
crossref_primary_10_1007_s10462_023_10583_4
crossref_primary_10_1080_13556509_2023_2203998
crossref_primary_10_1145_3587932
crossref_primary_10_1016_j_commtr_2023_100095
crossref_primary_10_1016_j_cosrev_2025_100756
crossref_primary_10_1007_s11063_023_11208_1
crossref_primary_10_1007_s11704_023_2246_2
crossref_primary_10_1007_s10579_025_09818_3
crossref_primary_10_3390_bdcc7020114
crossref_primary_10_1145_3750043
crossref_primary_10_1007_s11227_022_04846_0
crossref_primary_10_1016_j_neucom_2025_129680
crossref_primary_10_3390_info14040226
Cites_doi 10.18653/v1/2020.acl-srw.22
10.18653/v1/D16-1139
10.18653/v1/2020.acl-main.148
10.18653/v1/N18-1033
10.1162/coli.2007.33.4.493
10.18653/v1/2020.coling-main.349
10.1007/s10590-021-09260-6
10.18653/v1/D16-1050
10.18653/v1/D18-1045
10.1162/tacl_a_00474
10.18653/v1/D17-1146
10.18653/v1/D19-1632
10.18653/v1/D16-1160
10.18653/v1/P16-1009
10.1609/aaai.v32i1.11985
10.18653/v1/W15-3049
10.1515/pralin-2017-0031
10.18653/v1/D17-1039
10.1007/s10590-011-9090-0
10.1038/s42256-020-00257-z
10.3115/v1/P15-1166
10.18653/v1/P16-1159
10.3115/1626431.1626468
10.18653/v1/D17-1319
10.18653/v1/W19-5358
10.1162/tacl_a_00447
10.18653/v1/N18-2084
10.18653/v1/W17-4706
10.18653/v1/2021.findings-acl.304
10.18653/v1/W19-5309
10.1162/tacl_a_00065
10.18653/v1/P19-1120
10.18653/v1/W19-5308
10.18653/v1/2021.acl-long.21
10.1006/csla.2000.0138
10.18653/v1/W19-5301
10.18653/v1/2021.eacl-main.90
10.18653/v1/W19-5206
10.3115/1654650.1654666
10.18653/v1/2021.wat-1.1
10.18653/v1/W17-4710
10.18653/v1/K16-1002
10.1007/s10579-014-9287-y
10.18653/v1/P16-1162
10.18653/v1/W19-5404
10.18653/v1/2020.acl-main.747
10.18653/v1/W18-6316
10.18653/v1/W18-6312
10.18653/v1/P19-1297
10.7551/mitpress/6591.001.0001
10.18653/v1/D16-1163
10.18653/v1/P19-1309
10.18653/v1/2020.emnlp-main.615
10.1145/3430984.3431026
10.18653/v1/W19-5348
10.18653/v1/W17-4707
10.1162/neco.1992.4.1.131
10.1007/978-981-33-6162-1_8
10.18653/v1/2020.findings-emnlp.195
10.1007/s10590-020-09255-9
10.18653/v1/W15-3014
10.18653/v1/W18-2703
10.18653/v1/W19-5313
10.18653/v1/D18-1398
10.18653/v1/W17-4715
10.18653/v1/2021.emnlp-main.125
10.18653/v1/P18-2104
10.18653/v1/2021.naacl-main.92
10.18653/v1/2021.naacl-main.89
10.18653/v1/N19-1388
10.1162/tacl_a_00437
10.18653/v1/N19-4009
10.18653/v1/D18-1399
10.18653/v1/W19-5319
10.18653/v1/D18-1396
10.18653/v1/2021.acl-long.349
10.18653/v1/W19-5325
10.18653/v1/2020.acl-main.704
10.18653/v1/2020.coling-main.579
10.18653/v1/P19-1294
10.1016/0022-1694(80)90036-0
10.3115/1626355.1626373
10.1162/tacl_a_00343
10.3115/1075096.1075117
10.1162/tacl_a_00288
10.18653/v1/2020.acl-main.688
10.18653/v1/2020.findings-emnlp.371
10.18653/v1/2020.acl-main.143
10.1162/tacl_a_00452
10.18653/v1/D18-1549
10.18653/v1/2020.acl-main.275
10.18653/v1/W19-5343
10.18653/v1/W19-5302
10.18653/v1/W18-6319
10.18653/v1/2020.emnlp-main.207
10.18653/v1/P19-1310
10.18653/v1/W18-6401
10.18653/v1/2020.winlp-1.21
10.1038/s41467-019-08987-4
10.18653/v1/P16-1185
10.18653/v1/W17-4704
10.18653/v1/P17-4012
10.3115/1626355.1626359
10.18653/v1/N18-1202
10.18653/v1/W17-4703
10.18653/v1/N19-1207
10.18653/v1/W17-4708
10.18653/v1/D18-1039
10.18653/v1/N16-1101
10.18653/v1/P17-2090
10.3115/v1/W14-3348
10.18653/v1/2020.coling-main.398
10.18653/v1/W19-5316
10.18653/v1/D16-1162
10.18653/v1/N19-1387
10.18653/v1/D18-1512
10.18653/v1/2021.naacl-main.38
10.1145/1102351.1102373
10.18653/v1/W18-6321
10.18653/v1/2021.eacl-srw.22
10.18653/v1/D18-1103
10.18653/v1/N18-1055
10.18653/v1/W18-6488
10.18653/v1/P19-1301
10.18653/v1/W17-3204
10.18653/v1/2020.coling-tutorials.3
10.18653/v1/W19-4315
10.18653/v1/D16-1137
10.18653/v1/2021.naacl-main.16
10.3115/v1/D14-1162
10.18653/v1/W19-5346
10.18653/v1/P18-4020
10.18653/v1/2020.emnlp-main.393
10.18653/v1/P18-1007
10.1017/9781108608480
10.18653/v1/2020.emnlp-main.75
10.18653/v1/D19-1080
10.18653/v1/W18-6301
10.1162/tacl_a_00051
10.18653/v1/W16-2209
10.18653/v1/D19-1331
10.18653/v1/W18-6478
10.18653/v1/2020.acl-main.417
10.18653/v1/2020.acl-main.170
10.18653/v1/P19-1021
10.18653/v1/2021.acl-short.16
10.3115/1073083.1073135
10.18653/v1/W19-5304
10.1162/coli_a_00356
10.1007/978-3-030-32236-6_42
10.18653/v1/D19-1146
10.18653/v1/2021.acl-long.66
10.1162/tacl_a_00167
10.18653/v1/2021.americasnlp-1.23
10.18653/v1/N19-1043
10.18653/v1/D18-2012
10.1609/aaai.v34i05.6479
10.18653/v1/W19-5322
10.18653/v1/2020.emnlp-main.213
10.18653/v1/W19-5339
10.18653/v1/W18-6453
10.1007/BF00992696
10.18653/v1/P19-1284
10.24963/ijcai.2021/629
10.18653/v1/2020.emnlp-main.210
10.18653/v1/W18-6325
10.18653/v1/2020.acl-main.694
10.18653/v1/2020.emnlp-demos.6
10.18653/v1/2021.eacl-main.115
10.3115/1073445.1073462
10.18653/v1/D19-5201
10.18653/v1/2020.acl-main.326
10.18653/v1/W19-5305
10.3115/1220575.1220660
10.18653/v1/2021.acl-long.507
10.18653/v1/P18-1115
10.1038/s41467-020-18073-9
ContentType Journal Article
Copyright 2022. This work is published under https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: 2022. This work is published under https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID AAYXX
CITATION
7SC
7T9
8FD
JQ2
L7M
L~C
L~D
1XC
VOOES
DOA
DOI 10.1162/coli_a_00446
DatabaseName CrossRef
Computer and Information Systems Abstracts
Linguistics and Language Behavior Abstracts (LLBA)
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Linguistics and Language Behavior Abstracts (LLBA)
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList
CrossRef
Technology Research Database
Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Languages & Literatures
Computer Science
EISSN 1530-9312
EndPage 732
ExternalDocumentID oai_doaj_org_article_c67ef92aeb924e50a96fada3b039dfa7
oai:HAL:hal-03479757v3
10_1162_coli_a_00446
coli_a_00446.pdf
GroupedDBID 0R
29F
2FS
2WC
4.4
4S
5GY
5VS
6J9
8US
AACJB
AAKMM
AAPBV
AAWTV
AAYFX
ABDBF
ABFLS
ABGDV
ABPTK
ABQDU
ACATF
ACGFO
ACHQT
ACM
ACVLL
ADBBV
ADHRN
ADL
AEGXH
AENEX
AFFNX
AFJFK
AFWIH
AIAGR
AIKLT
ALMA_UNASSIGNED_HOLDINGS
ARCSS
ASPBG
AVWKF
AZFZN
BCNDV
BDXCO
CAG
CS3
DC
DU5
EAP
EBS
ECS
EDO
EMK
EPL
EST
ESX
FEDTE
FRP
GROUPED_DOAJ
GUFHI
HGAVV
HVGLF
HZ
I-F
I07
KQ8
MCG
MK
M~E
O9-
OK1
P2P
PQEST
PQQKQ
RMI
RNS
TUS
W7O
WG8
WH7
X
Z
--Z
-~X
.4S
.DC
0R~
AALFJ
AAYXX
ACUHS
ADMLS
AEBYY
AEJOY
AENSD
AFWXC
AKRVB
CCLIF
CITATION
HZ~
JMNJE
LHSKQ
MINIK
MK~
MLAFT
7SC
7T9
8FD
JQ2
L7M
L~C
L~D
1XC
AEFXT
C1A
COF
EJD
MVM
VOOES
WHG
X7L
ZWS
ZY4
ID FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3
IEDL.DBID DOA
ISICitedReferencesCount 62
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000993788500006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0891-2017
IngestDate Fri Oct 03 12:43:35 EDT 2025
Tue Oct 14 21:00:22 EDT 2025
Sat Nov 08 20:02:19 EST 2025
Sat Nov 29 01:40:19 EST 2025
Tue Nov 18 21:53:31 EST 2025
Fri Sep 02 10:41:51 EDT 2022
Thu Sep 01 12:10:32 EDT 2022
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
License Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3
Notes 2022
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-9553-1768
0000-0002-9022-3405
OpenAccessLink https://doaj.org/article/c67ef92aeb924e50a96fada3b039dfa7
PQID 2891834237
PQPubID 35960
PageCount 60
ParticipantIDs crossref_citationtrail_10_1162_coli_a_00446
proquest_journals_2891834237
hal_primary_oai_HAL_hal_03479757v3
crossref_primary_10_1162_coli_a_00446
doaj_primary_oai_doaj_org_article_c67ef92aeb924e50a96fada3b039dfa7
mit_journals_coliv48i3_324120_2022_09_01_zip_coli_a_00446
mit_journals_10_1162_coli_a_00446
PublicationCentury 2000
PublicationDate 2022-09-01
PublicationDateYYYYMMDD 2022-09-01
PublicationDate_xml – month: 09
  year: 2022
  text: 2022-09-01
  day: 01
PublicationDecade 2020
PublicationPlace One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA
PublicationPlace_xml – name: One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA
– name: Cambridge
PublicationTitle Computational linguistics - Association for Computational Linguistics
PublicationYear 2022
Publisher MIT Press
MIT Press Journals, The
Massachusetts Institute of Technology Press (MIT Press)
The MIT Press
Publisher_xml – name: MIT Press
– name: MIT Press Journals, The
– name: Massachusetts Institute of Technology Press (MIT Press)
– name: The MIT Press
References Zhang (2022090113562462600_bib314) 2020
Denkowski (2022090113562462600_bib65) 2014
Ataman (2022090113562462600_bib12) 2019
Bengio (2022090113562462600_bib24) 2015
Jha (2022090113562462600_bib126) 2020
Nakazawa (2022090113562462600_bib199) 2021
Koehn (2022090113562462600_bib152) 2017
Sen (2022090113562462600_bib257) 2019
Rezende (2022090113562462600_bib240) 2014
Ott (2022090113562462600_bib217) 2019
Artetxe (2022090113562462600_bib9) 2019; 7
Kreutzer (2022090113562462600_bib155) 2022; 10
Xu (2022090113562462600_bib304) 2019
Barrault (2022090113562462600_bib18) 2020
Platanios (2022090113562462600_bib224) 2018
Chronopoulou (2022090113562462600_bib50) 2020
Kudo (2022090113562462600_bib156) 2018
Dutta (2022090113562462600_bib73) 2020
Firat (2022090113562462600_bib87) 2016
Rei (2022090113562462600_bib238) 2020
Luong (2022090113562462600_bib182) 2016
Agić (2022090113562462600_bib2) 2019
Huck (2022090113562462600_bib122) 2017
Steedman (2022090113562462600_bib275) 2000
Niehues (2022090113562462600_bib206) 2018
Choshen (2022090113562462600_bib47) 2020
Neubig (2022090113562462600_bib204) 2018
Lignos (2022090113562462600_bib176) 2010
Kingma (2022090113562462600_bib137) 2014
Post (2022090113562462600_bib227) 2018
Rios (2022090113562462600_bib241) 2020
Bojar (2022090113562462600_bib31) 2018
Wiseman (2022090113562462600_bib296) 2016
Schmidhuber (2022090113562462600_bib252) 1992; 4
Cettolo (2022090113562462600_bib42) 2014
Adelani (2022090113562462600_bib1) 2021
Aharoni (2022090113562462600_bib3) 2019
Kvapilíková (2022090113562462600_bib161) 2020
Vinyals (2022090113562462600_bib288) 2016
Fadaee (2022090113562462600_bib82) 2017
Grönroos (2022090113562462600_bib106) 2014
Kocmi (2022090113562462600_bib143) 2018
Dong (2022090113562462600_bib71) 2015
LeCun (2022090113562462600_bib169) 2006; 1
Budiwati (2022090113562462600_bib37) 2019
Freitag (2022090113562462600_bib92) 2020
Kim (2022090113562462600_bib136) 2019
Kumaraswamy (2022090113562462600_bib159) 1980; 46
Ranathunga (2022090113562462600_bib235) 2021
Goldwater (2022090113562462600_bib100) 2005
Akhbardeh (2022090113562462600_bib5) 2021
Miceli Barone (2022090113562462600_bib189) 2017
Dhar (2022090113562462600_bib67) 2020
Goodfellow (2022090113562462600_bib101) 2014
Santoro (2022090113562462600_bib249) 2016
Lo (2022090113562462600_bib180) 2019
Xu (2022090113562462600_bib303) 2019
Ezeani (2022090113562462600_bib81) 2020
Fan (2022090113562462600_bib83) 2021; 22
Ramachandran (2022090113562462600_bib233) 2017
Sennrich (2022090113562462600_bib261) 2016
Sellam (2022090113562462600_bib256) 2020
Koehn (2022090113562462600_bib153) 2006
Popel (2022090113562462600_bib225) 2020; 11
Knowles (2022090113562462600_bib140) 2020
Bowman (2022090113562462600_bib32) 2016
Singh (2022090113562462600_bib269) 2020
Tran (2022090113562462600_bib284) 2021
Ortega (2022090113562462600_bib214) 2020; 34
Tang (2022090113562462600_bib278) 2021
Song (2022090113562462600_bib271) 2019
Conneau (2022090113562462600_bib54) 2018
Li (2022090113562462600_bib171) 2019
Denkowski (2022090113562462600_bib64) 2011
Wu (2022090113562462600_bib299) 2018
Cover (2022090113562462600_bib55) 2006
Feng (2022090113562462600_bib84) 2020; abs/2007.01852
Koehn (2022090113562462600_bib151) 2018
Devlin (2022090113562462600_bib66) 2019
Nakazawa (2022090113562462600_bib198) 2019
2022090113562462600_bib173
Niehues (2022090113562462600_bib207) 2017
Ortega (2022090113562462600_bib213) 2021
Eikema (2022090113562462600_bib77) 2019
Sennrich (2022090113562462600_bib262) 2010
Aji (2022090113562462600_bib4) 2020
Hokamp (2022090113562462600_bib121) 2019
Zhang (2022090113562462600_bib313) 2020
Burlot (2022090113562462600_bib38) 2017
Bojar (2022090113562462600_bib30) 2011
Ha (2022090113562462600_bib110) 2016
Lapuschkin (2022090113562462600_bib166) 2019; 10
Song (2022090113562462600_bib272) 2019
Barrault (2022090113562462600_bib17) 2019
Wu (2022090113562462600_bib298) 2019
Koehn (2022090113562462600_bib146) 2020
Zhang (2022090113562462600_bib310) 2016
Arivazhagan (2022090113562462600_bib6) 2019
Johnson (2022090113562462600_bib127) 2017; 5
Sánchez-Cartagena (2022090113562462600_bib245) 2019
Víctor (2022090113562462600_bib247) 2018
Chen (2022090113562462600_bib44) 2020
Kumar (2022090113562462600_bib158) 2021
Yang (2022090113562462600_bib305) 2020
Garcia (2022090113562462600_bib95) 2021
Nakazawa (2022090113562462600_bib200) 2020
Ranzato (2022090113562462600_bib236) 2016
Klein (2022090113562462600_bib138) 2017
Mayer (2022090113562462600_bib188) 2014
He (2022090113562462600_bib115) 2016
Koehn (2022090113562462600_bib149) 2007
Wu (2022090113562462600_bib300) 2020
Huszar (2022090113562462600_bib124) 2015
Libovický (2022090113562462600_bib175) 2020
Artetxe (2022090113562462600_bib7) 2018
Conneau (2022090113562462600_bib53) 2019
Jean (2022090113562462600_bib125) 2015
Knowles (2022090113562462600_bib139) 2020
Nădejde (2022090113562462600_bib197) 2017
Ojha (2022090113562462600_bib211) 2020
Kunchukuttan (2022090113562462600_bib160) 2020
Eikema (2022090113562462600_bib78) 2020
Gu (2022090113562462600_bib107) 2018
Kudo (2022090113562462600_bib157) 2018
Schwenk (2022090113562462600_bib254) 2021
Koehn (2022090113562462600_bib154) 2003
Sennrich (2022090113562462600_bib260) 2016
Muller (2022090113562462600_bib194) 2021
Conneau (2022090113562462600_bib52) 2020
Bahdanau (2022090113562462600_bib15) 2015
Shen (2022090113562462600_bib266) 2016
He (2022090113562462600_bib116) 2019
He (2022090113562462600_bib117) 2020
Post (2022090113562462600_bib228) 2012
Rezende (2022090113562462600_bib239) 2015
Bertoldi (2022090113562462600_bib25) 2009
Sánchez-Cartagena (2022090113562462600_bib244) 2020
Sánchez-Martínez (2022090113562462600_bib248) 2020
Scherrer (2022090113562462600_bib251) 2020
DiAntonino (2022090113562462600_bib68) 2017
Edunov (2022090113562462600_bib76) 2018
Zhang (2022090113562462600_bib311) 2016
Dandapat (2022090113562462600_bib62) 2018
Sánchez-Cartagena (2022090113562462600_bib243) 2018
Junczys-Dowmunt (2022090113562462600_bib128) 2018
Yang (2022090113562462600_bib306) 2021
Currey (2022090113562462600_bib56) 2017
Varga (2022090113562462600_bib286) 2005
Sen (2022090113562462600_bib258) 2019
Khanna (2022090113562462600_bib132) 2021
Christodouloupoulos (2022090113562462600_bib48) 2015; 49
Nakazawa (2022090113562462600_bib201) 2018
Daumé (2022090113562462600_bib63) 2005
Lakew (2022090113562462600_bib163) 2018
Artetxe (2022090113562462600_bib8) 2019
Forcada (2022090113562462600_bib89) 2011; 25
Junczys-Dowmunt (2022090113562462600_bib129) 2018
Mikolov (2022090113562462600_bib190) 2013
Popović (2022090113562462600_bib226) 2015
Wolf (2022090113562462600_bib297) 2020
Edunov (2022090113562462600_bib75) 2018
Saleva (2022090113562462600_bib242) 2021
Toral (2022090113562462600_bib281) 2018
Williams (2022090113562462600_bib294) 2018
Freitag (2022090113562462600_bib94) 2021
Louizos (2022090113562462600_bib181) 2018
Edman (2022090113562462600_bib74) 2020
Kim (2022090113562462600_bib134) 2019
Ramesh (2022090113562462600_bib234) 2022; 10
Dinu (2022090113562462600_bib70) 2019
Läubli (2022090113562462600_bib168) 2018
Onome Orife (2022090113562462600_bib212) 2020
Dabre (2022090113562462600_bib59) 2019
Liu (2022090113562462600_bib179) 2020; 8
Dabre (2022090113562462600_bib61) 2017
Nguyen (2022090113562462600_bib205) 2017
Philip (2022090113562462600_bib223) 2021
Libovický (2022090113562462600_bib174) 2021
Niu (2022090113562462600_bib208) 2019
Uszkoreit (2022090113562462600_bib285) 2010
Oflazer (2022090113562462600_bib210) 2007
Bawden (2022090113562462600_bib20) 2020
Cheng (2022090113562462600_bib45) 2016
Ataman (2022090113562462600_bib13) 2017; 108
Qi (2022090113562462600_bib230) 2018
Gülçehre (2022090113562462600_bib108) 2015
Scherrer (2022090113562462600_bib250) 2018
Tiedemann (2022090113562462600_bib279) 2012
Wei (2022090113562462600_bib292) 2020
Zaremoodi (2022090113562462600_bib308) 2018
Koehn (2022090113562462600_bib147) 2020
Haddow (2022090113562462600_bib112) 2020
Geirhos (2022090113562462600_bib97) 2020; 2
Tiedemann (2022090113562462600_bib280) 2020
Koehn (2022090113562462600_bib148) 2019
Goyal (2022090113562462600_bib103) 2020
Hieber (2022090113562462600_bib119) 2020
Feng (2022090113562462600_bib85) 2017
Peters (2022090113562462600_bib222) 2018
Zhang (2022090113562462600_bib312) 2019
Raffel (2022090113562462600_bib232) 2020; 21
Stahlberg (2022090113562462600_bib273) 2019
Williams (2022090113562462600_bib295) 1992; 8
Buck (2022090113562462600_bib36) 2014
Forcada (2022090113562462600_bib90) 2016
Mueller (2022090113562462600_bib192) 2020
Habash (2022090113562462600_bib111) 2021
Lin (2022090113562462600_bib178) 2020
Papineni (2022090113562462600_bib219) 2002
Goel (2022090113562462600_bib99) 2000; 14
Zhang (2022090113562462600_bib309) 2020
Müller (2022090113562462600_bib195) 2020
Bojanowski (2022090113562462600_bib29) 2017; 5
Lepikhin (2022090113562462600_bib170) 2020
Guzmán (2022090113562462600_bib109) 2019
Lin (2022090113562462600_bib177) 2019
Fraser (2022090113562462600_bib91) 2020
Hassan (2022090113562462600_bib114) 2018
Sánchez-Cartagena (2022090113562462600_bib246) 2020
Stahlberg (2022090113562462600_bib274) 2018
Chakravarthi (2022090113562462600_bib43) 2021
Finn (2022090113562462600_bib86) 2017
Schwenk (2022090113562462600_bib255) 2021
Karakanta (2022090113562462600_bib131) 2019
Ma (2022090113562462600_bib184) 2021
Mukiibi (2022090113562462600_bib193) 2021
Tracey (2022090113562462600_bib283) 2019
Ethayarajh (2022090113562462600_bib80) 2020
Neishi (2022090113562462600_bib202) 2017
Wang (2022090113562462600_bib290) 2021
Shi (2022090113562462600_bib267) 2020
Zoph (2022090113562462600_bib316) 2016
Clark (2022090113562462600_bib51) 2007; 33
Emezue (2022090113562462600_bib79) 2020
Lample (2022090113562462600_bib165) 2018
Wenzek (2022090113562462600_bib293) 2021
Xu (2022090113562462600_bib302) 2017
Hupkes (2022090113562462600_bib123) 2019
Dabre (2022090113562462600_bib60) 2018
Ding (2022090113562462600_bib69) 2019
Briakou (2022090113562462600_bib33) 2019
Caswell (2022090113562462600_bib41) 2019
Kocmi (2022090113562462600_bib142) 2020
Bei (2022090113562462600_bib23) 2019
Babych (2022090113562462600_bib14) 2021
Brown (2022090113562462600_bib34) 1993; 19
Sennrich (2022090113562462600_bib263) 2011
Wang (2022090113562462600_bib291) 2020
References_xml – year: 2019
  ident: 2022090113562462600_bib123
  article-title: The compositionality of neural networks: Integrating symbolism and connectionism
  publication-title: CoRR
– start-page: 1084
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib50
  article-title: The LMU Munich system for the WMT 2020 unsupervised machine translation shared task
– start-page: 162
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
  year: 2020
  ident: 2022090113562462600_bib103
  article-title: Efficient neural machine translation for low-resource languages via exploiting related languages
  doi: 10.18653/v1/2020.acl-srw.22
– start-page: 1317
  volume-title: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
  year: 2016
  ident: 2022090113562462600_bib133
  article-title: Sequence-level knowledge distillation
  doi: 10.18653/v1/D16-1139
– start-page: 1628
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib309
  article-title: Improving massively multilingual neural machine translation and zero-shot translation
  doi: 10.18653/v1/2020.acl-main.148
– start-page: 355
  volume-title: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
  year: 2018
  ident: 2022090113562462600_bib76
  article-title: Classical structured prediction losses for sequence to sequence learning
  doi: 10.18653/v1/N18-1033
– volume: 33
  start-page: 493
  issue: 4
  year: 2007
  ident: 2022090113562462600_bib51
  article-title: Wide-coverage efficient statistical parsing with CCG and log-linear models
  publication-title: Computational Linguistics
  doi: 10.1162/coli.2007.33.4.493
– start-page: 171
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib142
  article-title: CUNI submission for the Inuktitut language in WMT news 2020
– start-page: 3938
  volume-title: Proceedings of the 28th International Conference on Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib246
  article-title: Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation
  doi: 10.18653/v1/2020.coling-main.349
– start-page: 1
  year: 2021
  ident: 2022090113562462600_bib132
  article-title: Recent advances in Apertium, a free/open-source rule-based machine translation platform for low-resource languages
  publication-title: Machine Translation
  doi: 10.1007/s10590-021-09260-6
– volume-title: Proceedings of the 13th International Workshop on Spoken Language Translation
  year: 2016
  ident: 2022090113562462600_bib110
  article-title: Toward multilingual neural machine translation with universal encoder and decoder
– start-page: 3158
  volume-title: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
  year: 2014
  ident: 2022090113562462600_bib188
  article-title: Creating a massively parallel Bible corpus
– start-page: 81
  volume-title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
  year: 2020
  ident: 2022090113562462600_bib74
  article-title: Low-resource unsupervised NMT: Diagnosing the problem and providing a linguistically motivated solution
– start-page: 521
  volume-title: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
  year: 2016
  ident: 2022090113562462600_bib310
  article-title: Variational neural machine translation
  doi: 10.18653/v1/D16-1050
– start-page: 1
  volume-title: Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation: 5th Workshop on Asian Translation: 5th Workshop on Asian Translation
  year: 2018
  ident: 2022090113562462600_bib201
  article-title: Overview of the 5th workshop on Asian translation
– start-page: 97
  volume-title: Proceedings of the 14th International Workshop on Spoken Language Translation
  year: 2017
  ident: 2022090113562462600_bib68
  article-title: Monolingual embeddings for low resourced neural machine translation
– start-page: 489
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
  year: 2018
  ident: 2022090113562462600_bib75
  article-title: Understanding back-translation at scale
  doi: 10.18653/v1/D18-1045
– ident: 2022090113562462600_bib173
– year: 2020
  ident: 2022090113562462600_bib112
  article-title: PMIndia - A collection of parallel corpora of languages of India
  publication-title: CoRR
– year: 2021
  ident: 2022090113562462600_bib102
  article-title: The FLORES-101 evaluation benchmark for low-resource and multilingual machine translation
  publication-title: CoRR
  doi: 10.1162/tacl_a_00474
– year: 2015
  ident: 2022090113562462600_bib124
  article-title: How (not) to train your generative model: Scheduled sampling, likelihood, adversary?
  publication-title: CoRR
– start-page: 1390
  volume-title: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
  year: 2017
  ident: 2022090113562462600_bib85
  article-title: Memory-augmented neural machine translation
  doi: 10.18653/v1/D17-1146
– start-page: 6098
  volume-title: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
  year: 2019
  ident: 2022090113562462600_bib109
  article-title: The FLORES evaluation datasets for low-resource machine translation: Nepali–English and Sinhala–English
  doi: 10.18653/v1/D19-1632
– start-page: 1535
  volume-title: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
  year: 2016
  ident: 2022090113562462600_bib311
  article-title: Exploiting source-side monolingual data in neural machine translation
  doi: 10.18653/v1/D16-1160
– start-page: 86
  volume-title: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
  year: 2016
  ident: 2022090113562462600_bib260
  article-title: Improving neural machine translation models with monolingual data
  doi: 10.18653/v1/P16-1009
– volume: 32
  start-page: 521
  issue: 1
  year: 2018
  ident: 2022090113562462600_bib276
  article-title: Variational recurrent neural machine translation
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
  doi: 10.1609/aaai.v32i1.11985
– start-page: 392
  volume-title: Proceedings of the Tenth Workshop on Statistical Machine Translation
  year: 2015
  ident: 2022090113562462600_bib226
  article-title: chrF: Character n-gram F-score for automatic MT evaluation
  doi: 10.18653/v1/W15-3049
– volume: 108
  start-page: 331
  year: 2017
  ident: 2022090113562462600_bib13
  article-title: Linguistically motivated vocabulary reduction for neural machine translation from Turkish to English
  publication-title: The Prague Bulletin of Mathematical Linguistics
  doi: 10.1515/pralin-2017-0031
– volume: abs/2007.01852
  year: 2020
  ident: 2022090113562462600_bib84
  article-title: Language-agnostic BERT sentence embedding
  publication-title: CoRR
– start-page: 151
  volume-title: Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
  year: 2020
  ident: 2022090113562462600_bib195
  article-title: Domain robustness in neural machine translation
– start-page: 383
  volume-title: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
  year: 2017
  ident: 2022090113562462600_bib233
  article-title: Unsupervised pretraining for sequence to sequence learning
  doi: 10.18653/v1/D17-1039
– volume: 25
  start-page: 127
  issue: 2
  year: 2011
  ident: 2022090113562462600_bib89
  article-title: Apertium: A free/open-source platform for rule-based machine translation
  publication-title: Machine Translation
  doi: 10.1007/s10590-011-9090-0
– volume: 2
  start-page: 665
  year: 2020
  ident: 2022090113562462600_bib97
  article-title: Shortcut learning in deep neural networks
  publication-title: Nature Machine Intelligence
  doi: 10.1038/s42256-020-00257-z
– start-page: 213
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib118
  article-title: The Ubiqus English-Inuktitut system for WMT20
– start-page: 1723
  volume-title: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
  year: 2015
  ident: 2022090113562462600_bib71
  article-title: Multi-task learning for multiple language translation
  doi: 10.3115/v1/P15-1166
– start-page: 1683
  volume-title: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
  year: 2016
  ident: 2022090113562462600_bib266
  article-title: Minimum risk training for neural machine translation
  doi: 10.18653/v1/P16-1159
– start-page: 202
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib104
  article-title: Contact relatedness can help improve multilingual NMT: Microsoft STCI-MT @ WMT20
– start-page: 182
  volume-title: Proceedings of the Fourth Workshop on Statistical Machine Translation
  year: 2009
  ident: 2022090113562462600_bib25
  article-title: Domain adaptation for statistical machine translation with monolingual resources
  doi: 10.3115/1626431.1626468
– start-page: 2945
  volume-title: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
  year: 2017
  ident: 2022090113562462600_bib302
  article-title: Zipporah: A fast and scalable data cleaning system for noisy Web-crawled parallel corpora
  doi: 10.18653/v1/D17-1319
– start-page: 507
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib180
  article-title: YiSi - a unified semantic MT quality evaluation and estimation metric for languages with different levels of available resources
  doi: 10.18653/v1/W19-5358
– volume: 10
  start-page: 50
  year: 2022
  ident: 2022090113562462600_bib155
  article-title: Quality at a glance: An audit of Web-crawled multilingual datasets
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00447
– start-page: 1842
  volume-title: Proceedings of the 33rd International Conference on International Conference on Machine Learning
  year: 2016
  ident: 2022090113562462600_bib249
  article-title: Meta-learning with memory-augmented neural networks
– start-page: 529
  volume-title: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
  year: 2018
  ident: 2022090113562462600_bib230
  article-title: When and why are pre-trained word embeddings useful for neural machine translation
  doi: 10.18653/v1/N18-2084
– start-page: 1112
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib139
  article-title: NRC systems for low resource German-Upper Sorbian machine translation 2020: Transfer learning with lexical modifications
– start-page: 868
  volume-title: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)
  year: 2007
  ident: 2022090113562462600_bib149
  article-title: Factored translation models
– start-page: 56
  volume-title: Proceedings of the Second Conference on Machine Translation
  year: 2017
  ident: 2022090113562462600_bib122
  article-title: Target-side word segmentation strategies for neural machine translation
  doi: 10.18653/v1/W17-4706
– start-page: 3450
  volume-title: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
  year: 2021
  ident: 2022090113562462600_bib278
  article-title: Multilingual translation from denoising pre-training
  doi: 10.18653/v1/2021.findings-acl.304
– start-page: 141
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib37
  article-title: DBMS-KU interpolation for WMT19 news translation task
  doi: 10.18653/v1/W19-5309
– start-page: 4171
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
  year: 2019
  ident: 2022090113562462600_bib66
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
– start-page: 1126
  volume-title: Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research
  year: 2017
  ident: 2022090113562462600_bib86
  article-title: Model-agnostic meta-learning for fast adaptation of deep networks
– volume: 5
  start-page: 339
  year: 2017
  ident: 2022090113562462600_bib127
  article-title: Google’s multilingual neural machine translation system: Enabling zero-shot translation
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00065
– start-page: 1246
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib134
  article-title: Effective cross-lingual transfer of neural machine translation models without shared vocabularies
  doi: 10.18653/v1/P19-1120
– start-page: 134
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib33
  article-title: The University of Maryland’s Kazakh-English neural machine translation system at WMT19
  doi: 10.18653/v1/W19-5308
– start-page: 9791
  volume-title: Advances in Neural Information Processing Systems
  year: 2019
  ident: 2022090113562462600_bib162
  article-title: Compositional generalization through meta sequence-to-sequence learning
– start-page: 244
  volume-title: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
  year: 2021
  ident: 2022090113562462600_bib218
  article-title: Contrastive learning for many-to-many multilingual neural machine translation
  doi: 10.18653/v1/2021.acl-long.21
– start-page: 89
  volume-title: Proceedings of the Sixth Conference on Machine Translation
  year: 2021
  ident: 2022090113562462600_bib293
  article-title: Findings of the WMT 2021 shared task on large-scale multilingual machine translation
– start-page: 1104
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib175
  article-title: The LMU Munich system for the WMT20 very low resource supervised MT task
– volume: 14
  start-page: 115
  issue: 2
  year: 2000
  ident: 2022090113562462600_bib99
  article-title: Minimum Bayes-risk automatic speech recognition
  publication-title: Computer Speech and Language
  doi: 10.1006/csla.2000.0138
– start-page: 538
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib315
  article-title: Look it up: Bilingual and monolingual dictionaries improve neural machine translation
– start-page: 1
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib18
  article-title: Findings of the 2020 Conference on Machine Translation (WMT20)
  doi: 10.18653/v1/W19-5301
– start-page: 1049
  volume-title: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
  year: 2021
  ident: 2022090113562462600_bib10
  article-title: Few-shot learning through contextual data augmentation
  doi: 10.18653/v1/2021.eacl-main.90
– volume-title: Proceedings of the 6th International Conference on Learning Representations
  year: 2018
  ident: 2022090113562462600_bib181
  article-title: Learning sparse neural networks through l0 regularization
– start-page: 99
  volume-title: Proceedings of the 4th Workshop on Asian Translation (WAT(2017)
  year: 2017
  ident: 2022090113562462600_bib202
  article-title: A bag of useful tricks for practical neural machine translation: Embedding layer initialization and large batch size
– start-page: 53
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)
  year: 2019
  ident: 2022090113562462600_bib41
  article-title: Tagged backtranslation
  doi: 10.18653/v1/W19-5206
– start-page: 85
  volume-title: Proceedings of the Sixth Workshop on Statistical Machine Translation
  year: 2011
  ident: 2022090113562462600_bib64
  article-title: Meteor 1.3: Automatic metric for reliable optimization and evaluation of machine translation systems
– start-page: 102
  volume-title: Proceedings on the Workshop on Statistical Machine Translation
  year: 2006
  ident: 2022090113562462600_bib153
  article-title: Manual and automatic evaluation of machine translation between European languages
  doi: 10.3115/1654650.1654666
– volume-title: Advances in Neural Information Processing Systems
  year: 2016
  ident: 2022090113562462600_bib115
  article-title: Dual learning for machine translation
– start-page: 118
  volume-title: Proceedings of the 15th International Workshop on Spoken Language Translation
  year: 2018
  ident: 2022090113562462600_bib294
  article-title: Samsung and University of Edinburgh’s system for the IWSLT 2018 low resource MT task
– start-page: 299
  volume-title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
  year: 2020
  ident: 2022090113562462600_bib248
  article-title: An English-Swahili parallel corpus and its use for neural machine translation in the news domain
– start-page: 287
  volume-title: Proceedings of the 21st Annual Conference of the European Association for Machine Translation
  year: 2018
  ident: 2022090113562462600_bib62
  article-title: Iterative data augmentation for neural machine translation: A low resource case study for English-Telugu
– start-page: 1
  volume-title: Proceedings of the 8th Workshop on Asian Translation (WAT2021)
  year: 2021
  ident: 2022090113562462600_bib199
  article-title: Overview of the 8th workshop on Asian translation
  doi: 10.18653/v1/2021.wat-1.1
– start-page: 99
  volume-title: Proceedings of the Second Conference on Machine Translation
  year: 2017
  ident: 2022090113562462600_bib189
  article-title: Deep architectures for neural machine translation
  doi: 10.18653/v1/W17-4710
– start-page: 10
  volume-title: Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning
  year: 2016
  ident: 2022090113562462600_bib32
  article-title: Generating sentences from a continuous space
  doi: 10.18653/v1/K16-1002
– start-page: 177
  volume-title: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions
  year: 2007
  ident: 2022090113562462600_bib150
  article-title: Moses: Open source toolkit for statistical machine translation
– volume-title: Proceedings of the 2nd International Conference on Learning Representations
  year: 2014
  ident: 2022090113562462600_bib137
  article-title: Auto-encoding variational Bayes
– start-page: 1144
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib268
  article-title: Adobe AMPS’s submission for very low resource supervised translation task at WMT(20
– start-page: 1101
  volume-title: Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)
  year: 2010
  ident: 2022090113562462600_bib285
  article-title: Large scale parallel document mining for machine translation
– volume: 49
  start-page: 375
  issue: 2
  year: 2015
  ident: 2022090113562462600_bib48
  article-title: A massively parallel corpus: The Bible in 100 languages
  publication-title: Language Resources and Evaluation
  doi: 10.1007/s10579-014-9287-y
– start-page: 1715
  volume-title: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
  year: 2016
  ident: 2022090113562462600_bib261
  article-title: Neural machine translation of rare words with subword units
  doi: 10.18653/v1/P16-1162
– year: 2021
  ident: 2022090113562462600_bib1
  article-title: MENYO-20k: A multi-domain English-Yorùbá corpus for machine translation and domain adaptation
  publication-title: CoRR
– start-page: 54
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
  year: 2019
  ident: 2022090113562462600_bib148
  article-title: Findings of the WMT 2019 shared task on parallel corpus filtering for low-resource conditions
  doi: 10.18653/v1/W19-5404
– start-page: 8440
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib52
  article-title: Unsupervised cross-lingual representation learning at scale
  doi: 10.18653/v1/2020.acl-main.747
– start-page: 156
  volume-title: Proceedings of the Third Conference on Machine Translation: Research Papers
  year: 2018
  ident: 2022090113562462600_bib163
  article-title: Neural machine translation into language varieties
  doi: 10.18653/v1/W18-6316
– start-page: 48
  volume-title: Proceedings of the 2nd Workshop on Technologies for MT of Low Resource Languages
  year: 2019
  ident: 2022090113562462600_bib283
  article-title: Corpus building for low resource languages in the DARPA LORELEI program
– volume-title: Proceedings of the 33rd International Conference on Neural Information Processing Systems
  year: 2019
  ident: 2022090113562462600_bib53
  article-title: Cross-lingual language model pre-training
– start-page: 2
  volume-title: Proceedings of the 11th International Workshop on Spoken Language Translation
  year: 2014
  ident: 2022090113562462600_bib42
  article-title: Report on the 11th IWSLT evaluation campaign, IWSLT 2014
– start-page: 113
  volume-title: Proceedings of the Third Conference on Machine Translation: Research Papers
  year: 2018
  ident: 2022090113562462600_bib281
  article-title: Attaining the unattainable? Reassessing claims of human parity in neural machine translation
  doi: 10.18653/v1/W18-6312
– start-page: 3083
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib258
  article-title: Multilingual unsupervised NMT using shared encoder and language-specific decoders
  doi: 10.18653/v1/P19-1297
– volume-title: The Syntactic Process
  year: 2000
  ident: 2022090113562462600_bib275
  doi: 10.7551/mitpress/6591.001.0001
– start-page: 1568
  volume-title: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
  year: 2016
  ident: 2022090113562462600_bib316
  article-title: Transfer learning for low-resource neural machine translation
  doi: 10.18653/v1/D16-1163
– start-page: 92
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib20
  article-title: The University of Edinburgh’s English-Tamil and English-Inuktitut submissions to the WMT20 news translation task
– start-page: 3197
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib8
  article-title: Margin-based parallel corpus mining with multilingual sentence embeddings
  doi: 10.18653/v1/P19-1309
– start-page: 7622
  volume-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
  year: 2020
  ident: 2022090113562462600_bib22
  article-title: Language model prior for low-resource neural machine translation
  doi: 10.18653/v1/2020.emnlp-main.615
– start-page: 178
  volume-title: Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data
  year: 2021
  ident: 2022090113562462600_bib223
  article-title: Revisiting low resource status of Indian languages in machine translation
  doi: 10.1145/3430984.3431026
– start-page: 424
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib301
  article-title: Microsoft Research Asia’s systems for WMT19
  doi: 10.18653/v1/W19-5348
– volume-title: Proceedings of the 4th International Conference on Learning Representations
  year: 2016
  ident: 2022090113562462600_bib182
  article-title: Multi-task sequence to sequence learning
– start-page: 68
  volume-title: Proceedings of the Second Conference on Machine Translation
  year: 2017
  ident: 2022090113562462600_bib197
  article-title: Predicting target language CCG supertags improves neural machine translation
  doi: 10.18653/v1/W17-4707
– volume: 4
  start-page: 131
  issue: 1
  year: 1992
  ident: 2022090113562462600_bib252
  article-title: Learning to control fast-weight memories: An alternative to dynamic recurrent networks
  publication-title: Neural Computation
  doi: 10.1162/neco.1992.4.1.131
– start-page: 33
  volume-title: Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages
  year: 2020
  ident: 2022090113562462600_bib211
  article-title: Findings of the LoResMT 2020 shared task on zero-shot for low-resource languages
– start-page: 590
  volume-title: Proceedings of the International Conference on Recent Advances in Natural Language Processing
  year: 2005
  ident: 2022090113562462600_bib286
  article-title: Parallel corpora for medium density languages
– start-page: 282
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib267
  article-title: OPPO’s machine translation systems for WMT20
  doi: 10.1007/978-981-33-6162-1_8
– start-page: 2144
  volume-title: Findings of the Association for Computational Linguistics: EMNLP 2020
  year: 2020
  ident: 2022090113562462600_bib203
  article-title: Participatory research for low-resourced machine translation: A case study in African languages
  doi: 10.18653/v1/2020.findings-emnlp.195
– volume-title: Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers
  year: 2010
  ident: 2022090113562462600_bib262
  article-title: MT-based sentence alignment for OCR-generated parallel texts
– volume: 34
  start-page: 325
  issue: 4
  year: 2020
  ident: 2022090113562462600_bib214
  article-title: Neural machine translation with a polysynthetic low resource language
  publication-title: Machine Translation
  doi: 10.1007/s10590-020-09255-9
– start-page: 175
  volume-title: Proceedings of the 18th Nordic Conference of Computational Linguistics (NODALIDA 2011)
  year: 2011
  ident: 2022090113562462600_bib263
  article-title: Iterative, MT-based sentence alignment of parallel texts
– start-page: 396
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib167
  article-title: Hindi-Marathi cross lingual model
– start-page: 134
  volume-title: Proceedings of the Tenth Workshop on Statistical Machine Translation
  year: 2015
  ident: 2022090113562462600_bib125
  article-title: Montreal neural machine translation systems for WMT’15
  doi: 10.18653/v1/W15-3014
– start-page: 18
  volume-title: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation
  year: 2018
  ident: 2022090113562462600_bib120
  article-title: Iterative back-translation for neural machine translation
  doi: 10.18653/v1/W18-2703
– start-page: 168
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib57
  article-title: NICT’s supervised neural machine translation systems for the WMT19 news translation task
  doi: 10.18653/v1/W19-5313
– start-page: 3622
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
  year: 2018
  ident: 2022090113562462600_bib107
  article-title: Meta-learning for low-resource neural machine translation
  doi: 10.18653/v1/D18-1398
– volume-title: Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
  year: 2021
  ident: 2022090113562462600_bib43
– start-page: 148
  volume-title: Proceedings of the Second Conference on Machine Translation
  year: 2017
  ident: 2022090113562462600_bib56
  article-title: Copied monolingual data improves low-resource neural machine translation
  doi: 10.18653/v1/W17-4715
– start-page: 1671
  volume-title: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
  year: 2021
  ident: 2022090113562462600_bib46
  article-title: mT6: Multilingual pre-trained text-to-text transformer with translation pairs
  doi: 10.18653/v1/2021.emnlp-main.125
– volume-title: Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)
  year: 2006
  ident: 2022090113562462600_bib55
– start-page: 656
  volume-title: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
  year: 2018
  ident: 2022090113562462600_bib308
  article-title: Adaptive knowledge sharing in multi-task learning: Improving low-resource neural machine translation
  doi: 10.18653/v1/P18-2104
– start-page: 1172
  volume-title: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  year: 2021
  ident: 2022090113562462600_bib237
  article-title: The curious case of hallucinations in neural machine translation
  doi: 10.18653/v1/2021.naacl-main.92
– start-page: 1126
  volume-title: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  year: 2021
  ident: 2022090113562462600_bib95
  article-title: Harnessing multilinguality in unsupervised machine translation for rare languages
  doi: 10.18653/v1/2021.naacl-main.89
– start-page: 3874
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
  year: 2019
  ident: 2022090113562462600_bib3
  article-title: Massively multilingual neural machine translation
  doi: 10.18653/v1/N19-1388
– volume: 9
  start-page: 1460
  year: 2021
  ident: 2022090113562462600_bib93
  article-title: Experts, errors, and context: A large-scale study of human evaluation for machine translation
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00437
– start-page: 48
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)
  year: 2019
  ident: 2022090113562462600_bib217
  article-title: FAIRSEQ: A fast, extensible toolkit for sequence modeling
  doi: 10.18653/v1/N19-4009
– volume-title: Proceedings of the 6th International Conference on Learning Representations
  year: 2018
  ident: 2022090113562462600_bib7
  article-title: Unsupervised neural machine translation
  doi: 10.18653/v1/D18-1399
– start-page: 204
  volume-title: Proceedings of Machine Translation Summit XVII Volume 1: Research Track
  year: 2019
  ident: 2022090113562462600_bib69
  article-title: A call for prudent choice of subword merge operations in neural machine translation
– start-page: 1092
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib73
  article-title: UdS-DFKI@WMT20: Unsupervised MT and very low resource supervised MT for German-Upper Sorbian
– year: 2020
  ident: 2022090113562462600_bib81
  article-title: Igbo-English machine translation: An evaluation benchmark
  publication-title: CoRR
– start-page: 209
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib121
  article-title: Evaluating the supervised and zero-shot performance of multi-lingual translation models
  doi: 10.18653/v1/W19-5319
– start-page: 1139
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib269
  article-title: The NITS-CNLP system for the unsupervised MT task at WMT 2020
– start-page: 3602
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
  year: 2018
  ident: 2022090113562462600_bib299
  article-title: Beyond error propagation in neural machine translation: Characteristics of language also matter
  doi: 10.18653/v1/D18-1396
– start-page: 569
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib186
  article-title: When does unsupervised machine translation work?
– start-page: 35
  volume-title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
  year: 2020
  ident: 2022090113562462600_bib135
  article-title: When and why is unsupervised neural machine translation useless?
– start-page: 4528
  volume-title: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
  year: 2021
  ident: 2022090113562462600_bib26
  article-title: Energy-based reranking: Improving neural machine translation using energy-based models
  doi: 10.18653/v1/2021.acl-long.349
– start-page: 257
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib171
  article-title: The NiuTrans machine translation systems for WMT(19
  doi: 10.18653/v1/W19-5325
– volume-title: Proceedings of the 3rd International Conference on Learning Representations
  year: 2015
  ident: 2022090113562462600_bib15
  article-title: Neural machine translation by jointly learning to align and translate
– start-page: 2214
  volume-title: Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
  year: 2012
  ident: 2022090113562462600_bib279
  article-title: Parallel data, tools and interfaces in OPUS
– start-page: 1
  volume-title: Proceedings of the 7th Workshop on Asian Translation
  year: 2020
  ident: 2022090113562462600_bib200
  article-title: Overview of the 7th workshop on Asian translation
– start-page: 127
  volume-title: Proceedings of the 19th Annual Conference of the European Association for Machine Translation: Projects/Products
  year: 2016
  ident: 2022090113562462600_bib90
  article-title: Apertium: A free/open source platform for machine translation and basic language technology
  doi: 10.1007/s10590-011-9090-0
– year: 2021
  ident: 2022090113562462600_bib184
  article-title: DeltaLM: Encoder-decoder pre-training for language generation and translation by augmenting pretrained multilingual encoders
  publication-title: arXiv preprint arXiv:2106.13736
– start-page: 7881
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib256
  article-title: BLEURT: Learning robust metrics for text generation
  doi: 10.18653/v1/2020.acl-main.704
– start-page: 5926
  volume-title: Proceedings of the 36th International Conference on Machine Learning
  year: 2019
  ident: 2022090113562462600_bib272
  article-title: MASS: Masked sequence to sequence pre-training for language generation
– start-page: 6588
  volume-title: Proceedings of the 28th International Conference on Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib40
  article-title: Language ID in the wild: Unexpected challenges on the path to a thousand-language web text corpus
  doi: 10.18653/v1/2020.coling-main.579
– volume-title: Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing
  year: 2021
  ident: 2022090113562462600_bib14
– start-page: 3063
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib70
  article-title: Training neural machine translation to apply terminology constraints
  doi: 10.18653/v1/P19-1294
– volume: 46
  start-page: 79
  issue: 1
  year: 1980
  ident: 2022090113562462600_bib159
  article-title: A generalized probability density function for double-bounded random processes
  publication-title: Journal of Hydrology
  doi: 10.1016/0022-1694(80)90036-0
– start-page: 136
  volume-title: Proceedings of the Second Workshop on Statistical Machine Translation
  year: 2007
  ident: 2022090113562462600_bib39
  article-title: (Meta-) evaluation of machine translation
  doi: 10.3115/1626355.1626373
– volume: 8
  start-page: 726
  year: 2020
  ident: 2022090113562462600_bib179
  article-title: Multilingual denoising pre-training for neural machine translation
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00343
– start-page: 338
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib314
  article-title: The NiuTrans machine translation systems for WMT20
– start-page: 160
  volume-title: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics
  year: 2003
  ident: 2022090113562462600_bib209
  article-title: Minimum error rate training in statistical machine translation
  doi: 10.3115/1075096.1075117
– volume: 7
  start-page: 597
  year: 2019
  ident: 2022090113562462600_bib9
  article-title: Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00288
– start-page: 1123
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib161
  article-title: CUNI systems for the unsupervised and very low resource translation task in WMT20
– start-page: 7701
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib4
  article-title: In neural machine translation, what does transfer learning transfer?
  doi: 10.18653/v1/2020.acl-main.688
– volume-title: Proceedings of the 8th International Conference on Learning Representations
  year: 2020
  ident: 2022090113562462600_bib313
  article-title: Learning with feature-dependent label noise: A progressive approach
– year: 2018
  ident: 2022090113562462600_bib114
  article-title: Achieving human parity on automatic Chinese to English news translation
  publication-title: CoRR
– start-page: 218
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib172
  article-title: SJTU-NICT’s supervised and unsupervised neural machine translation systems for the WMT20 news translation task
  doi: 10.18653/v1/2020.findings-emnlp.371
– start-page: 9378
  volume-title: Proceedings of the 34th AAAI Conference on Artificial Intelligence
  year: 2020
  ident: 2022090113562462600_bib305
  article-title: Towards making the most of BERT in neural machine translation
– volume-title: Proceedings of the WILDRE5– 5th Workshop on Indian Language Data: Resources and Evaluation
  year: 2020
  ident: 2022090113562462600_bib126
– year: 2021
  ident: 2022090113562462600_bib193
  article-title: An English-Luganda parallel corpus
– start-page: 1
  volume-title: Proceedings of the Sixth Conference on Machine Translation
  year: 2021
  ident: 2022090113562462600_bib5
  article-title: Findings of the 2021 conference on machine translation (WMT21)
– start-page: 1570
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib72
  article-title: Bilingual dictionary based neural machine translation without using parallel sentences
  doi: 10.18653/v1/2020.acl-main.143
– volume: 10
  start-page: 145
  year: 2022
  ident: 2022090113562462600_bib234
  article-title: Samanantar: The largest publicly available parallel corpora collection for 11 Indic languages
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00452
– volume-title: Proceedings of the Sixth Arabic Natural Language Processing Workshop
  year: 2021
  ident: 2022090113562462600_bib111
– start-page: 5039
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
  year: 2018
  ident: 2022090113562462600_bib165
  article-title: Phrase-based & neural unsupervised machine translation
  doi: 10.18653/v1/D18-1549
– start-page: 83
  volume-title: Proceedings of the 15th International Workshop on Spoken Language Translation
  year: 2018
  ident: 2022090113562462600_bib250
  article-title: The University of Helsinki submissions to the IWSLT 2018 low-resource translation task
– start-page: 3042
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib117
  article-title: Dynamic programming encoding for subword segmentation in neural machine translation
  doi: 10.18653/v1/2020.acl-main.275
– start-page: 8
  volume-title: Proceedings of the 13th International Workshop on Spoken Language Translation
  year: 2016
  ident: 2022090113562462600_bib96
  article-title: Factored neural machine translation architectures
– start-page: 386
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib282
  article-title: Neural machine translation for English–Kazakh with morphological segmentation and synthetic data
  doi: 10.18653/v1/W19-5343
– start-page: 233
  volume-title: Proceedings of Machine Translation Summit XVII: Research Track
  year: 2019
  ident: 2022090113562462600_bib187
  article-title: Identifying fluently inadequate output in neural and statistical machine translation
– start-page: 528
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib241
  article-title: Subword segmentation and a single bridge language affect zero-shot neural machine translation
– start-page: 550
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib92
  article-title: Complete multilingual neural machine translation
– start-page: 62
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib183
  article-title: Results of the WMT(19 metrics shared task: Segment-level and strong MT systems pose big challenges
  doi: 10.18653/v1/W19-5302
– start-page: 3743
  volume-title: Proceedings of the 12th Language Resources and Evaluation Conference
  year: 2020
  ident: 2022090113562462600_bib270
  article-title: A multilingual parallel corpora collection effort for Indian languages
– start-page: 186
  volume-title: Proceedings of the Third Conference on Machine Translation: Research Papers
  year: 2018
  ident: 2022090113562462600_bib227
  article-title: A call for clarity in reporting BLEU scores
  doi: 10.18653/v1/W18-6319
– start-page: 156
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib140
  article-title: NRC systems for the 2020 Inuktitut-English news translation task
– year: 2015
  ident: 2022090113562462600_bib108
  article-title: On using monolingual corpora in neural machine translation
  publication-title: CoRR
– volume-title: Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)
  year: 2021
  ident: 2022090113562462600_bib213
– start-page: 2612
  volume-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
  year: 2020
  ident: 2022090113562462600_bib113
  article-title: Not low-resource anymore: Aligner ensembling, batch filtering, and new datasets for Bengali-English machine translation
  doi: 10.18653/v1/2020.emnlp-main.207
– start-page: 3204
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib2
  article-title: JW300: A wide-coverage parallel corpus for low-resource languages
  doi: 10.18653/v1/P19-1310
– start-page: 330
  volume-title: Proceedings of the Sixth Workshop on Statistical Machine Translation
  year: 2011
  ident: 2022090113562462600_bib30
  article-title: Improving translation model by monolingual data
  doi: 10.18653/v1/W18-6401
– start-page: 1171
  volume-title: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1
  year: 2015
  ident: 2022090113562462600_bib24
  article-title: Scheduled sampling for sequence prediction with recurrent neural networks
– start-page: 1174
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib280
  article-title: The Tatoeba Translation Challenge – Realistic data sets for low resource and multilingual MT
– volume-title: Proceedings of International Conference on Learning Representations
  year: 2013
  ident: 2022090113562462600_bib190
  article-title: Efficient estimation of word representations in vector space
– start-page: 83
  volume-title: Proceedings of the The Fourth Widening Natural Language Processing Workshop
  year: 2020
  ident: 2022090113562462600_bib79
  article-title: FFR v1.1: Fon-French neural machine translation
  doi: 10.18653/v1/2020.winlp-1.21
– volume: 10
  start-page: 1
  issue: 1
  year: 2019
  ident: 2022090113562462600_bib166
  article-title: Unmasking clever Hans predictors and assessing what machines really learn
  publication-title: Nature Communications
  doi: 10.1038/s41467-019-08987-4
– start-page: 1877
  volume-title: Advances in Neural Information Processing Systems
  year: 2020
  ident: 2022090113562462600_bib35
  article-title: Language models are few-shot learners
– start-page: 1965
  volume-title: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
  year: 2016
  ident: 2022090113562462600_bib45
  article-title: Semi-supervised learning for neural machine translation
  doi: 10.18653/v1/P16-1185
– start-page: 32
  volume-title: Proceedings of the Second Conference on Machine Translation
  year: 2017
  ident: 2022090113562462600_bib277
  article-title: Modeling target-side inflection in neural machine translation
  doi: 10.18653/v1/W17-4704
– start-page: 305
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib300
  article-title: The Volctrans machine translation system for WMT20
– start-page: 67
  volume-title: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics-System Demonstrations
  year: 2017
  ident: 2022090113562462600_bib138
  article-title: OpenNMT: Open-source toolkit for neural machine translation
  doi: 10.18653/v1/P17-4012
– start-page: 25
  volume-title: Proceedings of the Second Workshop on Statistical Machine Translation
  year: 2007
  ident: 2022090113562462600_bib210
  article-title: Exploring different representational units in English-to-Turkish statistical machine translation
  doi: 10.3115/1626355.1626359
– start-page: 2227
  volume-title: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
  year: 2018
  ident: 2022090113562462600_bib222
  article-title: Deep contextualized word representations
  doi: 10.18653/v1/N18-1202
– start-page: 20
  volume-title: Proceedings of the Second Conference on Machine Translation
  year: 2017
  ident: 2022090113562462600_bib38
  article-title: Word representations in factored neural machine translation
  doi: 10.18653/v1/W17-4703
– volume: 19
  start-page: 263
  issue: 2
  year: 1993
  ident: 2022090113562462600_bib34
  article-title: The mathematics of statistical machine translation: Parameter estimation
  publication-title: Computational Linguistics
– start-page: 2047
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
  year: 2019
  ident: 2022090113562462600_bib304
  article-title: Differentiable sampling with flexible reference word order for neural machine translation
  doi: 10.18653/v1/N19-1207
– start-page: 80
  volume-title: Proceedings of the Second Conference on Machine Translation
  year: 2017
  ident: 2022090113562462600_bib207
  article-title: Exploiting linguistic resources for neural machine translation using multi-task learning
  doi: 10.18653/v1/W17-4708
– start-page: 425
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
  year: 2018
  ident: 2022090113562462600_bib224
  article-title: Contextual parameter generation for universal neural machine translation
  doi: 10.18653/v1/D18-1039
– start-page: 2
  volume-title: Proceedings of the 15th International Workshop on Spoken Language Translation
  year: 2018
  ident: 2022090113562462600_bib206
  article-title: The IWSLT 2018 evaluation campaign
– start-page: 866
  volume-title: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  year: 2016
  ident: 2022090113562462600_bib87
  article-title: Multi-way, multilingual neural machine translation with a shared attention mechanism
  doi: 10.18653/v1/N16-1101
– start-page: 567
  volume-title: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
  year: 2017
  ident: 2022090113562462600_bib82
  article-title: Data augmentation for low-resource neural machine translation
  doi: 10.18653/v1/P17-2090
– start-page: 272
  volume-title: Proceedings of the Third Conference on Machine Translation, Volume 2: Shared Task Papers
  year: 2018
  ident: 2022090113562462600_bib31
  article-title: Findings of the 2018 Conference on Machine Translation (WMT18)
  doi: 10.18653/v1/W18-6401
– volume-title: Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation: 5th Workshop on Asian Translation: 5th Workshop on Asian Translation
  year: 2018
  ident: 2022090113562462600_bib60
  article-title: NICT’s participation in WAT 2018: Approaches using multilingualism and recurrently stacked layers
– start-page: 376
  volume-title: Proceedings of the Ninth Workshop on Statistical Machine Translation
  year: 2014
  ident: 2022090113562462600_bib65
  article-title: Meteor universal: Language specific translation evaluation for any target language
  doi: 10.3115/v1/W14-3348
– start-page: 4506
  volume-title: Proceedings of the 28th International Conference on Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib78
  article-title: Is MAP decoding all you need? The inadequacy of the mode in neural machine translation
  doi: 10.18653/v1/2020.coling-main.398
– start-page: 191
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib105
  article-title: The IIIT-H Gujarati-English machine translation system for WMT19
  doi: 10.18653/v1/W19-5316
– start-page: 1557
  volume-title: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
  year: 2016
  ident: 2022090113562462600_bib11
  article-title: Incorporating discrete translation lexicons into neural machine translation
  doi: 10.18653/v1/D16-1162
– start-page: 3868
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
  year: 2019
  ident: 2022090113562462600_bib196
  article-title: Addressing word-order divergence in multilingual neural machine translation for extremely low resource languages
  doi: 10.18653/v1/N19-1387
– start-page: 1530
  volume-title: Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research
  year: 2015
  ident: 2022090113562462600_bib239
  article-title: Variational Inference with Normalizing Flows
– start-page: 4791
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
  year: 2018
  ident: 2022090113562462600_bib168
  article-title: Has machine translation achieved human parity? A case for document-level evaluation
  doi: 10.18653/v1/D18-1512
– start-page: 448
  volume-title: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  year: 2021
  ident: 2022090113562462600_bib194
  article-title: When being unseen from mBERT is just the beginning: Handling new languages with multilingual language models
  doi: 10.18653/v1/2021.naacl-main.38
– volume-title: Proceedings of the 7th International Conference on Learning Representations
  year: 2019
  ident: 2022090113562462600_bib116
  article-title: Revisiting Self-Training for neural sequence generation
– start-page: 205
  volume-title: Proceedings of the Sixth Conference on Machine Translation
  year: 2021
  ident: 2022090113562462600_bib284
  article-title: Facebook AI’s WMT21 news translation task submission
– start-page: 92
  volume-title: Proceedings of the 18th Biennial Machine Translation Summit (Volume 1: Research Track)
  year: 2021
  ident: 2022090113562462600_bib28
  article-title: Surprise language challenge: Developing a neural machine translation system between Pashto and English in two months
– start-page: 1129
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib251
  article-title: The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks
– start-page: 449
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
  year: 2019
  ident: 2022090113562462600_bib271
  article-title: Code-switching for enhancing NMT with pre-specified translation
– volume-title: Proceedings of the 2nd Workshop on Technologies for MT of Low Resource Languages
  year: 2019
  ident: 2022090113562462600_bib131
– start-page: 169
  volume-title: Proceedings of the 22nd International Conference on Machine Learning
  year: 2005
  ident: 2022090113562462600_bib63
  article-title: Learning as search optimization: Approximate large margin methods for structured prediction
  doi: 10.1145/1102351.1102373
– volume: 22
  start-page: 1
  year: 2021
  ident: 2022090113562462600_bib83
  article-title: Beyond English-centric multilingual machine translation
  publication-title: Journal of Machine Learning Research 22
– start-page: 204
  volume-title: Proceedings of the Third Conference on Machine Translation: Research Papers
  year: 2018
  ident: 2022090113562462600_bib274
  article-title: Simple fusion: Return of the language model
  doi: 10.18653/v1/W18-6321
– start-page: 401
  volume-title: Proceedings of the Seventh Workshop on Statistical Machine Translation
  year: 2012
  ident: 2022090113562462600_bib228
  article-title: Constructing parallel corpora for six Indian languages via crowdsourcing
– start-page: 164
  volume-title: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
  year: 2021
  ident: 2022090113562462600_bib242
  article-title: The effectiveness of morphology-aware segmentation in low-resource neural machine translation
  doi: 10.18653/v1/2021.eacl-srw.22
– start-page: 875
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
  year: 2018
  ident: 2022090113562462600_bib204
  article-title: Rapid adaptation of neural machine translation to new languages
  doi: 10.18653/v1/D18-1103
– start-page: 595
  volume-title: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
  year: 2018
  ident: 2022090113562462600_bib130
  article-title: Approaching neural grammatical error correction as a low-resource machine translation task
  doi: 10.18653/v1/N18-1055
– year: 2021
  ident: 2022090113562462600_bib235
  article-title: Neural machine translation for low-resource languages: A survey
  publication-title: CoRR
– start-page: 955
  volume-title: Proceedings of the Third Conference on Machine Translation: Shared Task Papers
  year: 2018
  ident: 2022090113562462600_bib243
  article-title: Prompsit’s submission to WMT 2018 parallel corpus filtering shared task
  doi: 10.18653/v1/W18-6488
– start-page: 35
  volume-title: Proceedings of the Morpho Challenge 2010 Workshop
  year: 2010
  ident: 2022090113562462600_bib176
  article-title: Learning from unseen data
– start-page: 3125
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib177
  article-title: Choosing transfer languages for cross-lingual learning
  doi: 10.18653/v1/P19-1301
– start-page: 61
  volume-title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
  year: 2020
  ident: 2022090113562462600_bib244
  article-title: A multi-source approach for Breton–French hybrid machine translation
– start-page: 220
  volume-title: Proceedings of the ACL 2010 Conference Short Papers
  year: 2010
  ident: 2022090113562462600_bib191
  article-title: Intelligent selection of language model training data
– start-page: 28
  volume-title: Proceedings of the First Workshop on Neural Machine Translation
  year: 2017
  ident: 2022090113562462600_bib152
  article-title: Six challenges for neural machine translation
  doi: 10.18653/v1/W17-3204
– year: 2020
  ident: 2022090113562462600_bib58
  article-title: A comprehensive survey of multilingual neural machine translation
  publication-title: CoRR
  doi: 10.18653/v1/2020.coling-tutorials.3
– start-page: 124
  volume-title: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
  year: 2019
  ident: 2022090113562462600_bib77
  article-title: Auto-encoding variational neural machine translation
  doi: 10.18653/v1/W19-4315
– start-page: 1296
  volume-title: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
  year: 2016
  ident: 2022090113562462600_bib296
  article-title: Sequence-to-sequence learning as beam-search optimization
  doi: 10.18653/v1/D16-1137
– volume-title: Proceedings of the 6th International Conference on Learning Representations
  year: 2018
  ident: 2022090113562462600_bib164
  article-title: Unsupervised machine translation using monolingual corpora only
– start-page: 173
  volume-title: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  year: 2021
  ident: 2022090113562462600_bib49
  article-title: Improving the lexical ability of pre-trained language models for unsupervised neural machine translation
  doi: 10.18653/v1/2021.naacl-main.16
– start-page: 1532
  volume-title: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
  year: 2014
  ident: 2022090113562462600_bib221
  article-title: GloVe: Global vectors for word representation
  doi: 10.3115/v1/D14-1162
– volume-title: Proceedings of the Sixth Conference on Machine Translation
  year: 2021
  ident: 2022090113562462600_bib145
  article-title: To ship or not to ship: An extensive evaluation of automatic metrics for machine translation
– volume-title: Proceedings of the 8th International Conference on Learning Representations
  year: 2020
  ident: 2022090113562462600_bib47
  article-title: On the weaknesses of reinforcement learning for neural machine translation
– volume-title: Proceedings of the 9th International Conference on Learning Representations
  year: 2019
  ident: 2022090113562462600_bib312
  article-title: BERTScore: Evaluating text generation with BERT
– start-page: 407
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib257
  article-title: IITP-MT system for Gujarati-English news translation task at WMT 2019
  doi: 10.18653/v1/W19-5346
– start-page: 116
  volume-title: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics-System Demonstrations
  year: 2018
  ident: 2022090113562462600_bib129
  article-title: Marian: Fast neural machine translation in C++
  doi: 10.18653/v1/P18-4020
– start-page: 5
  volume-title: Advances in Neural Information Processing Systems
  year: 2016
  ident: 2022090113562462600_bib288
  article-title: Matching networks for one shot learning
– start-page: 4846
  volume-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
  year: 2020
  ident: 2022090113562462600_bib80
  article-title: Utility is in the eye of the user: A critique of NLP leaderboards
  doi: 10.18653/v1/2020.emnlp-main.393
– start-page: 66
  volume-title: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
  year: 2018
  ident: 2022090113562462600_bib156
  article-title: Subword regularization: Improving neural network translation models with multiple subword candidates
  doi: 10.18653/v1/P18-1007
– volume-title: Neural Machine Translation
  year: 2020
  ident: 2022090113562462600_bib146
  doi: 10.1017/9781108608480
– start-page: 1022
  volume-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
  year: 2020
  ident: 2022090113562462600_bib291
  article-title: Multi-task learning for multilingual neural machine translation
  doi: 10.18653/v1/2020.emnlp-main.75
– start-page: 1177
  volume-title: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers
  year: 2014
  ident: 2022090113562462600_bib106
  article-title: Morfessor FlatCat: An HMM-based method for unsupervised and semi-supervised learning of morphology
– start-page: 866
  volume-title: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
  year: 2019
  ident: 2022090113562462600_bib136
  article-title: Pivot-based transfer learning for neural machine translation between Non-English languages
  doi: 10.18653/v1/D19-1080
– start-page: 733
  volume-title: Proceedings of the Sixth Conference on Machine Translation
  year: 2021
  ident: 2022090113562462600_bib94
  article-title: Results of the WMT21 metrics shared task: Evaluating metrics with expert-based human evaluations on TED and news domain
– start-page: 296
  volume-title: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
  year: 2017
  ident: 2022090113562462600_bib205
  article-title: Transfer learning across low-resource, related languages for neural machine translation
– volume-title: International Conference on Machine Learning
  year: 2018
  ident: 2022090113562462600_bib216
  article-title: Analyzing uncertainty in neural machine translation
  doi: 10.18653/v1/W18-6301
– year: 2019
  ident: 2022090113562462600_bib98
  article-title: A survey of methods to leverage monolingual data in low-resource neural machine translation
  publication-title: CoRR
– start-page: 6000
  volume-title: 31st Conference on Neural Information Processing Systems
  year: 2017
  ident: 2022090113562462600_bib287
  article-title: Attention is all you need
– start-page: 9
  volume-title: Proceedings of the 7th Workshop on the Challenges in the Management of Large Corpora (CMLC-7)
  year: 2019
  ident: 2022090113562462600_bib215
  article-title: Asynchronous pipeline for processing huge corpora on medium to low resource infrastructures
– volume-title: Proceedings of the 7th International Conference on Learning Representations
  year: 2019
  ident: 2022090113562462600_bib298
  article-title: Pay less attention with lightweight and dynamic convolutions
– volume: 5
  start-page: 135
  year: 2017
  ident: 2022090113562462600_bib29
  article-title: Enriching word vectors with subword information
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00051
– start-page: 83
  volume-title: Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers
  year: 2016
  ident: 2022090113562462600_bib259
  article-title: Linguistic input features improve neural machine translation
  doi: 10.18653/v1/W16-2209
– volume-title: Proceedings of the 4th International Conference on Learning Representations
  year: 2016
  ident: 2022090113562462600_bib236
  article-title: Sequence level training with recurrent neural networks
– start-page: 3356
  volume-title: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
  year: 2019
  ident: 2022090113562462600_bib273
  article-title: On NMT search errors and model errors: Cat got your tongue?
  doi: 10.18653/v1/D19-1331
– start-page: 888
  volume-title: Proceedings of the Third Conference on Machine Translation: Shared Task Papers
  year: 2018
  ident: 2022090113562462600_bib128
  article-title: Dual conditional cross-entropy filtering of noisy parallel corpora
  doi: 10.18653/v1/W18-6478
– start-page: 4555
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib16
  article-title: ParaCrawl: Web-scale acquisition of parallel corpora
  doi: 10.18653/v1/2020.acl-main.417
– start-page: 1882
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib229
  article-title: BPE-dropout: Simple and effective subword regularization
  doi: 10.18653/v1/2020.acl-main.170
– start-page: 211
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib264
  article-title: Revisiting low-resource neural machine translation: A case study
  doi: 10.18653/v1/P19-1021
– year: 2015
  ident: 2022090113562462600_bib307
  article-title: Reinforcement Learning Neural Turing Machines
  publication-title: CoRR
– start-page: 110
  volume-title: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
  year: 2021
  ident: 2022090113562462600_bib158
  article-title: Machine translation into low-resource language varieties
  doi: 10.18653/v1/2021.acl-short.16
– start-page: 584
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib27
  article-title: Language models not just for pre-training: Fast online neural noisy channel modeling
– start-page: 311
  volume-title: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics
  year: 2002
  ident: 2022090113562462600_bib219
  article-title: BLEU: A method for automatic evaluation of machine translation
  doi: 10.3115/1073083.1073135
– start-page: 1
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib17
  article-title: Findings of the 2019 Conference on Machine Translation (WMT19)
  doi: 10.18653/v1/W19-5301
– start-page: 3874
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
  year: 2019
  ident: 2022090113562462600_bib6
  article-title: Massively multilingual neural machine translation in the wild: Findings and challenges
– volume-title: Proceedings of the 2014 International Conference on Learning Representations
  year: 2014
  ident: 2022090113562462600_bib101
  article-title: An empirical investigation of catastrophic forgetting in gradient-based neural networks
– start-page: 103
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib21
  article-title: The University of Edinburgh’s submissions to the WMT19 news translation task
  doi: 10.18653/v1/W19-5304
– volume: 45
  start-page: 515
  issue: 3
  year: 2019
  ident: 2022090113562462600_bib88
  article-title: Taking MT evaluation metrics to extremes: Beyond correlation with human judgments
  publication-title: Computational Linguistics
  doi: 10.1162/coli_a_00356
– start-page: 457
  volume-title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
  year: 2020
  ident: 2022090113562462600_bib119
  article-title: Sockeye 2: A toolkit for neural machine translation
– start-page: 466
  volume-title: Natural Language Processing and Chinese Computing
  year: 2019
  ident: 2022090113562462600_bib303
  article-title: Analysis of back-translation methods for low-resource neural machine translation
  doi: 10.1007/978-3-030-32236-6_42
– start-page: 1410
  volume-title: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
  year: 2019
  ident: 2022090113562462600_bib59
  article-title: Exploiting multilingualism through multistage fine-tuning for low-resource neural machine translation
  doi: 10.18653/v1/D19-1146
– start-page: 802
  volume-title: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
  year: 2021
  ident: 2022090113562462600_bib141
  article-title: Adapting high-resource NMT models to translate low-resource related languages without parallel data
  doi: 10.18653/v1/2021.acl-long.66
– start-page: 726
  volume-title: Proceedings of the Sixth Conference on Machine Translation
  year: 2021
  ident: 2022090113562462600_bib174
  article-title: Findings of the WMT 2021 shared tasks in unsupervised MT and very low resource supervised MT
– volume: 2
  start-page: 79
  issue: Feb
  year: 2014
  ident: 2022090113562462600_bib220
  article-title: The language demographics of Amazon Mechanical Turk
  publication-title: Transactions of the Association for Computational Linguistics
  doi: 10.1162/tacl_a_00167
– start-page: 282
  volume-title: Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation
  year: 2017
  ident: 2022090113562462600_bib61
  article-title: An empirical study of language relatedness for transfer learning in neural machine translation
– volume: 1
  start-page: 0
  issue: 0
  year: 2006
  ident: 2022090113562462600_bib169
  article-title: A tutorial on energy-based learning
  publication-title: Predicting Structured Data
– start-page: 724
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib147
  article-title: Findings of the WMT 2020 shared task on parallel corpus filtering and alignment
– start-page: 202
  volume-title: Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
  year: 2021
  ident: 2022090113562462600_bib185
  article-title: Findings of the AmericasNLP 2021 shared task on open machine translation for indigenous languages of the Americas
  doi: 10.18653/v1/2021.americasnlp-1.23
– start-page: 442
  volume-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
  year: 2019
  ident: 2022090113562462600_bib208
  article-title: Bi-directional differentiable input reconstruction for low-resource neural machine translation
  doi: 10.18653/v1/N19-1043
– volume-title: AfricaNLP Workshop
  year: 2020
  ident: 2022090113562462600_bib212
  article-title: Masakhane–machine translation for Africa
– start-page: 66
  volume-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
  year: 2018
  ident: 2022090113562462600_bib157
  article-title: SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing
  doi: 10.18653/v1/D18-2012
– start-page: 446
  volume-title: Proceedings of the Sixth Conference on Machine Translation
  year: 2021
  ident: 2022090113562462600_bib306
  article-title: Multilingual machine translation systems from Microsoft for WMT21 shared task
  doi: 10.1609/aaai.v34i05.6479
– start-page: 765
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib91
  article-title: Findings of the WMT 2020 shared tasks in unsupervised MT and very low resource supervised MT
– start-page: 234
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib144
  article-title: CUNI Submission for low-resource languages in WMT news 2019
  doi: 10.18653/v1/W19-5322
– start-page: 2685
  volume-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
  year: 2020
  ident: 2022090113562462600_bib238
  article-title: COMET: A neural framework for MT evaluation
  doi: 10.18653/v1/2020.emnlp-main.213
– start-page: 356
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib245
  article-title: The Universitat d’Alacant submissions to the English-to-Kazakh news translation task at WMT 2019
  doi: 10.18653/v1/W19-5339
– start-page: 726
  volume-title: Proceedings of the Third Conference on Machine Translation: Shared Task Papers
  year: 2018
  ident: 2022090113562462600_bib151
  article-title: Findings of the WMT 2018 shared task on parallel corpus filtering
  doi: 10.18653/v1/W18-6453
– volume: 8
  start-page: 229
  issue: 3–4
  year: 1992
  ident: 2022090113562462600_bib295
  article-title: Simple statistical gradient-following algorithms for connectionist reinforcement learning
  publication-title: Machine Learning
  doi: 10.1007/BF00992696
– start-page: 2963
  volume-title: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  year: 2019
  ident: 2022090113562462600_bib19
  article-title: Interpretable neural predictions with differentiable binary variables
  doi: 10.18653/v1/P19-1284
– volume-title: Proceedings of the 7th International Conference on Learning Representations
  year: 2019
  ident: 2022090113562462600_bib12
  article-title: A latent morphology model for open-vocabulary neural machine translation
– year: 2020
  ident: 2022090113562462600_bib160
  article-title: The IndicNLP library
– start-page: 126
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib67
  article-title: Linguistically motivated subwords for English-Tamil translation: University of Groningen’s submission to WMT-2020
– volume-title: Proceedings of the 6th International Conference on Learning Representations
  year: 2018
  ident: 2022090113562462600_bib54
  article-title: Word translation without parallel data
– start-page: 4636
  volume-title: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
  year: 2021
  ident: 2022090113562462600_bib290
  article-title: A survey on low-resource neural machine translation
  doi: 10.24963/ijcai.2021/629
– start-page: 3710
  volume-title: Proceedings of the 12th Language Resources and Evaluation Conference
  year: 2020
  ident: 2022090113562462600_bib192
  article-title: An analysis of massively multilingual neural machine translation for low-resource languages
– start-page: 2649
  volume-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
  year: 2020
  ident: 2022090113562462600_bib178
  article-title: Pre-training multilingual neural machine translation by leveraging alignment information
  doi: 10.18653/v1/2020.emnlp-main.210
– start-page: 244
  volume-title: Proceedings of the Third Conference on Machine Translation: Research Papers
  year: 2018
  ident: 2022090113562462600_bib143
  article-title: Trivial transfer learning for low-resource neural machine translation
  doi: 10.18653/v1/W18-6325
– start-page: 1278
  volume-title: Proceedings of the 31st International Conference on Machine Learning, volume 32 of Proceedings of Machine Learning Research
  year: 2014
  ident: 2022090113562462600_bib240
  article-title: Stochastic backpropagation and approximate inference in deep generative models
– start-page: 113
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib44
  article-title: Facebook AI’s WMT(20 news translation task submission
– volume-title: International Conference
  year: 2020
  ident: 2022090113562462600_bib170
  article-title: GShard: Scaling giant models with conditional computation and automatic sharding
– start-page: 7771
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib265
  article-title: Variational neural machine translation with normalizing flows
  doi: 10.18653/v1/2020.acl-main.694
– ident: 2022090113562462600_bib231
– start-page: 38
  volume-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
  year: 2020
  ident: 2022090113562462600_bib297
  article-title: Transformers: State-of-the-art natural language processing
  doi: 10.18653/v1/2020.emnlp-demos.6
– start-page: 293
  volume-title: Proceedings of the Fifth Conference on Machine Translation
  year: 2020
  ident: 2022090113562462600_bib292
  article-title: HW-TSC’s participation in the WMT 2020 news translation shared task
– start-page: 1351
  volume-title: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
  year: 2021
  ident: 2022090113562462600_bib254
  article-title: WikiMatrix: Mining 135M parallel sentences in 1620 language pairs from Wikipedia
  doi: 10.18653/v1/2021.eacl-main.115
– start-page: 95
  volume-title: Proceedings of the 15th International Workshop on Spoken Language Translation
  year: 2018
  ident: 2022090113562462600_bib247
  article-title: Prompsit’s submission to the IWSLT 2018 low resource machine translation task
– start-page: 127
  volume-title: Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics
  year: 2003
  ident: 2022090113562462600_bib154
  article-title: Statistical phrase-based translation
  doi: 10.3115/1073445.1073462
– start-page: 1
  volume-title: Proceedings of the 6th Workshop on Asian Translation
  year: 2019
  ident: 2022090113562462600_bib198
  article-title: Overview of the 6th workshop on Asian translation
  doi: 10.18653/v1/D19-5201
– start-page: 3544
  volume-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
  year: 2020
  ident: 2022090113562462600_bib289
  article-title: On exposure bias, hallucination and domain shift in neural machine translation
  doi: 10.18653/v1/2020.acl-main.326
– start-page: 116
  volume-title: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
  year: 2019
  ident: 2022090113562462600_bib23
  article-title: GTCOM neural machine translation systems for WMT19
  doi: 10.18653/v1/W19-5305
– start-page: 676
  volume-title: Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing
  year: 2005
  ident: 2022090113562462600_bib100
  article-title: Improving statistical MT through morphological analysis
  doi: 10.3115/1220575.1220660
– volume: 21
  start-page: 1
  issue: 140
  year: 2020
  ident: 2022090113562462600_bib232
  article-title: Exploring the limits of transfer learning with a unified text-to-text transformer
  publication-title: Journal of Machine Learning Research
– start-page: 3579
  volume-title: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
  year: 2014
  ident: 2022090113562462600_bib36
  article-title: N-gram counts and language models from the Common Crawl
– start-page: 6490
  volume-title: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
  year: 2021
  ident: 2022090113562462600_bib255
  article-title: CCMatrix: Mining billions of high-quality parallel sentences on the web
  doi: 10.18653/v1/2021.acl-long.507
– start-page: 1243
  volume-title: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
  year: 2018
  ident: 2022090113562462600_bib253
  article-title: A stochastic decoder for neural machine translation
  doi: 10.18653/v1/P18-1115
– volume: 11
  start-page: 1
  year: 2020
  ident: 2022090113562462600_bib225
  article-title: Transforming machine translation: A deep learning system reaches news translation quality comparable to human professionals
  publication-title: Nature Communications
  doi: 10.1038/s41467-020-18073-9
SSID ssj0007037
Score 2.6668987
Snippet We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the...
SourceID doaj
hal
proquest
crossref
mit
SourceType Open Website
Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 673
SubjectTerms Computation and Language
Computer Science
Languages
Machine translation
Polls & surveys
Training
Translation
Title Survey of Low-Resource Machine Translation
URI https://direct.mit.edu/coli/article/doi/10.1162/coli_a_00446
https://www.proquest.com/docview/2891834237
https://inria.hal.science/hal-03479757
https://doaj.org/article/c67ef92aeb924e50a96fada3b039dfa7
Volume 48
WOSCitedRecordID wos000993788500006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: Directory of Open Access Journals
  customDbUrl:
  eissn: 1530-9312
  dateEnd: 20241231
  omitProxy: false
  ssIdentifier: ssj0007037
  issn: 0891-2017
  databaseCode: DOA
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYK6qEXRCmFpRSlVemhVYQTO34cKSrisEWVAImb5cdERIJdtLts1f76jp1kYYsQl16dieXMTOZhf54h5FNVOc6Dkzl1QuRcF5BbUDpXgQXHAUNm2zabkKen6vJS_3zQ6itiwtrywC3jDryQUOvSgsNMASpqtahtsMxRpkNt0z1yKnWfTHU2GPVY9jB3UR4gTxtjTTq9XHJAqU4_upWriIJcuWlmj0xy8jPH62StCxCzw3Zhr8kLGG2QrWG3rTjNPmfDRSXk6Rvy5exuMoff2bjOhuNfeb8bn_1IIEnIki9q8W6b5OL4-_nRSd71P8g9Mm2GOaJX3HPqbMCsALyK4RcLinnnlA1KMqkCDdZZyYrKOqHQ9zsNUANGCS6wt2R1NB7BNsk0dVIJXQuua86EttxTJVF6hQABhRyQrz1TjO-Kg8ceFdcmJQmiNA9ZOCD7C-rbtijGE3TfIn8XNLGUdRpAAZtOwOY5AQ_IR5TO0hwnh0MTx2i8BisrOWcD8gGFZ7r_b_rEavQSTXw256phBoPKoqSmxHjGUG1oYf40t_-8u9urxf0EmKuiQYy4op3_8aHvyKu4ghbAtktWZ5M7eE9e-vmsmU72kn7_BUAt_4c
linkProvider Directory of Open Access Journals
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=Survey+of+Low-Resource+Machine+Translation&rft.jtitle=Computational+linguistics+-+Association+for+Computational+Linguistics&rft.au=Haddow%2C+Barry&rft.au=Bawden%2C+Rachel&rft.au=Miceli+Barone%2C+Antonio+Valerio&rft.au=Helcl%2C+Jind%C5%99ich&rft.date=2022-09-01&rft.pub=Massachusetts+Institute+of+Technology+Press+%28MIT+Press%29&rft.issn=0891-2017&rft.eissn=1530-9312&rft.volume=48&rft.issue=3&rft.spage=673&rft.epage=732&rft_id=info:doi/10.1162%2Fcoli_a_00446&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-03479757v3
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0891-2017&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0891-2017&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0891-2017&client=summon