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 2022-09, Vol.48 (3), p.673-732
Main Authors: Haddow, Barry, Bawden, Rachel, Barone, Antonio Valerio Miceli, Helcl, Jindřich, Birch, Alexandra
Format: Article
Language:English
Subjects:
Computation and Language
Computer Science
Machine translation
Polls & surveys
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3
cites cdi_FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3
container_end_page 732
container_issue 3
container_start_page 673
container_title Computational linguistics - Association for Computational Linguistics
container_volume 48
creator Haddow, Barry
Bawden, Rachel
Barone, Antonio Valerio Miceli
Helcl, Jindřich
Birch, Alexandra
description 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.
doi_str_mv 10.1162/coli_a_00446
format article
fullrecord <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_proquest_journals_2891834237</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_c67ef92aeb924e50a96fada3b039dfa7</doaj_id><sourcerecordid>2891834237</sourcerecordid><originalsourceid>FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3</originalsourceid><addsrcrecordid>eNp1kV1rE0EUhgdRMEbv_AEBb1S69czXzsydpWhbiAharw9nPtZO2GbibJJSf72brpQW9OrAy8Nzvhh7zeGY81Z8CKXPSAigVPuEzbiW0DjJxVM2A-t4I4Cb5-zFMKwAwIA0M_b--67u0-2idItluWm-paHsakiLLxSu8jotLiuth562uaxfsmcd9UN69bfO2Y_Pny5Pz5vl17OL05NlE5Tj20aLYFVQ4Clq06ZgQelWRiuD95aiNdLYCJE8Gck1-XacDLxLqUtcax_lnF1M3lhohZuar6neYqGMd0GpP5HqNoc-YWhN6pyg5J1QSQO5tqNI0oN0sRsbzNm7yXVF_SPV-ckSDxlIZZzRZi9H9s3Ebmr5tUvDFlfjLdbjqijGGa1UQh6MRxMVahmGmrp7LQc8fAEffmHE3074dX7g-w_68R_oAdkrmyVKobgAFCAEgkPg-DtvHiv-AD3mm6E</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2891834237</pqid></control><display><type>article</type><title>Survey of Low-Resource Machine Translation</title><source>EBSCOhost MLA International Bibliography With Full Text</source><source>Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list)</source><source>Linguistics and Language Behavior Abstracts (LLBA)</source><creator>Haddow, Barry ; Bawden, Rachel ; Barone, Antonio Valerio Miceli ; Helcl, Jindřich ; Birch, Alexandra</creator><creatorcontrib>Haddow, Barry ; Bawden, Rachel ; Barone, Antonio Valerio Miceli ; Helcl, Jindřich ; Birch, Alexandra</creatorcontrib><description>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.</description><identifier>ISSN: 0891-2017</identifier><identifier>EISSN: 1530-9312</identifier><identifier>DOI: 10.1162/coli_a_00446</identifier><language>eng</language><publisher>One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA: MIT Press</publisher><subject>Computation and Language ; Computer Science ; Machine translation ; Polls &amp; surveys ; Training</subject><ispartof>Computational linguistics - Association for Computational Linguistics, 2022-09, Vol.48 (3), p.673-732</ispartof><rights>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.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3</citedby><cites>FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3</cites><orcidid>0000-0001-9553-1768 ; 0000-0002-9022-3405</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925,31269</link.rule.ids><backlink>$$Uhttps://inria.hal.science/hal-03479757$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Haddow, Barry</creatorcontrib><creatorcontrib>Bawden, Rachel</creatorcontrib><creatorcontrib>Barone, Antonio Valerio Miceli</creatorcontrib><creatorcontrib>Helcl, Jindřich</creatorcontrib><creatorcontrib>Birch, Alexandra</creatorcontrib><title>Survey of Low-Resource Machine Translation</title><title>Computational linguistics - Association for Computational Linguistics</title><description>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.</description><subject>Computation and Language</subject><subject>Computer Science</subject><subject>Machine translation</subject><subject>Polls &amp; surveys</subject><subject>Training</subject><issn>0891-2017</issn><issn>1530-9312</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>7T9</sourceid><sourceid>DOA</sourceid><recordid>eNp1kV1rE0EUhgdRMEbv_AEBb1S69czXzsydpWhbiAharw9nPtZO2GbibJJSf72brpQW9OrAy8Nzvhh7zeGY81Z8CKXPSAigVPuEzbiW0DjJxVM2A-t4I4Cb5-zFMKwAwIA0M_b--67u0-2idItluWm-paHsakiLLxSu8jotLiuth562uaxfsmcd9UN69bfO2Y_Pny5Pz5vl17OL05NlE5Tj20aLYFVQ4Clq06ZgQelWRiuD95aiNdLYCJE8Gck1-XacDLxLqUtcax_lnF1M3lhohZuar6neYqGMd0GpP5HqNoc-YWhN6pyg5J1QSQO5tqNI0oN0sRsbzNm7yXVF_SPV-ckSDxlIZZzRZi9H9s3Ebmr5tUvDFlfjLdbjqijGGa1UQh6MRxMVahmGmrp7LQc8fAEffmHE3074dX7g-w_68R_oAdkrmyVKobgAFCAEgkPg-DtvHiv-AD3mm6E</recordid><startdate>20220901</startdate><enddate>20220901</enddate><creator>Haddow, Barry</creator><creator>Bawden, Rachel</creator><creator>Barone, Antonio Valerio Miceli</creator><creator>Helcl, Jindřich</creator><creator>Birch, Alexandra</creator><general>MIT Press</general><general>MIT Press Journals, The</general><general>Massachusetts Institute of Technology Press (MIT Press)</general><general>The MIT Press</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7T9</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>1XC</scope><scope>VOOES</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-9553-1768</orcidid><orcidid>https://orcid.org/0000-0002-9022-3405</orcidid></search><sort><creationdate>20220901</creationdate><title>Survey of Low-Resource Machine Translation</title><author>Haddow, Barry ; Bawden, Rachel ; Barone, Antonio Valerio Miceli ; Helcl, Jindřich ; Birch, Alexandra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computation and Language</topic><topic>Computer Science</topic><topic>Machine translation</topic><topic>Polls &amp; surveys</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Haddow, Barry</creatorcontrib><creatorcontrib>Bawden, Rachel</creatorcontrib><creatorcontrib>Barone, Antonio Valerio Miceli</creatorcontrib><creatorcontrib>Helcl, Jindřich</creatorcontrib><creatorcontrib>Birch, Alexandra</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Linguistics and Language Behavior Abstracts (LLBA)</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><collection>Directory of Open Access Journals</collection><jtitle>Computational linguistics - Association for Computational Linguistics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Haddow, Barry</au><au>Bawden, Rachel</au><au>Barone, Antonio Valerio Miceli</au><au>Helcl, Jindřich</au><au>Birch, Alexandra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Survey of Low-Resource Machine Translation</atitle><jtitle>Computational linguistics - Association for Computational Linguistics</jtitle><date>2022-09-01</date><risdate>2022</risdate><volume>48</volume><issue>3</issue><spage>673</spage><epage>732</epage><pages>673-732</pages><issn>0891-2017</issn><eissn>1530-9312</eissn><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.</abstract><cop>One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA</cop><pub>MIT Press</pub><doi>10.1162/coli_a_00446</doi><tpages>60</tpages><orcidid>https://orcid.org/0000-0001-9553-1768</orcidid><orcidid>https://orcid.org/0000-0002-9022-3405</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0891-2017
ispartof Computational linguistics - Association for Computational Linguistics, 2022-09, Vol.48 (3), p.673-732
issn 0891-2017
1530-9312
language eng
recordid cdi_proquest_journals_2891834237
source EBSCOhost MLA International Bibliography With Full Text; Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list); Linguistics and Language Behavior Abstracts (LLBA)
subjects Computation and Language
Computer Science
Machine translation
Polls & surveys
Training
title Survey of Low-Resource Machine Translation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T01%3A44%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Survey%20of%20Low-Resource%20Machine%20Translation&rft.jtitle=Computational%20linguistics%20-%20Association%20for%20Computational%20Linguistics&rft.au=Haddow,%20Barry&rft.date=2022-09-01&rft.volume=48&rft.issue=3&rft.spage=673&rft.epage=732&rft.pages=673-732&rft.issn=0891-2017&rft.eissn=1530-9312&rft_id=info:doi/10.1162/coli_a_00446&rft_dat=%3Cproquest_hal_p%3E2891834237%3C/proquest_hal_p%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c491t-52c84c40bad576ec804563d83cbb8ad87378d0daba7315ab68910b9eefe155bd3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2891834237&rft_id=info:pmid/&rfr_iscdi=true