Neural machine translation: Challenges, progress and future

Neural machine translation: Challenges, progress and future

Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural networks has achieved a big breakthrough in translation performance...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Science China. Technological sciences 2020-10, Vol.63 (10), p.2028-2050
Hauptverfasser: Zhang, JiaJun, Zong, ChengQing
Format: Artikel
Sprache:eng
Schlagworte:
Artificial neural networks
Engineering
Languages
Machine translation
Review
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2050
container_issue 10
container_start_page 2028
container_title Science China. Technological sciences
container_volume 63
creator Zhang, JiaJun
Zong, ChengQing
description Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural networks has achieved a big breakthrough in translation performance and become the de facto paradigm of MT. This article makes a review of NMT framework, discusses the challenges in NMT, introduces some exciting recent progresses and finally looks forward to some potential future research trends.
doi_str_mv 10.1007/s11431-020-1632-x
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2452108349</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2452108349</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-ef01d227bc7265b32bd277ac8abe7b36fb2948a0e4237350d7b3b231231088b73</originalsourceid><addsrcrecordid>eNp1UE1LxDAQDaLgsu4P8FbwanRmkjatnmTxCxa96DkkbbrbpduuSQvrvzdLBU8OAzMM772ZeYxdItwggLoNiFIgBwKOmSB-OGEzzLOCYwFwGvtMSa4E4TlbhLCFGCIvAOWM3b-50Zs22Zly03QuGbzpQmuGpu_ukuXGtK3r1i5cJ3vfr70LITFdldTjMHp3wc5q0wa3-K1z9vn0-LF84av359flw4qXArOBuxqwIlK2VJSlVpCtSClT5sY6ZUVWWypkbsBJEkqkUMWhJYExIc-tEnN2NenGG75GFwa97UffxZWaZEoRJWQRUTihSt-H4F2t977ZGf-tEfTRJj3ZpKNN-miTPkQOTZwQsfFP_6f8P-kHLxRpRA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2452108349</pqid></control><display><type>article</type><title>Neural machine translation: Challenges, progress and future</title><source>SpringerNature Journals</source><source>Alma/SFX Local Collection</source><creator>Zhang, JiaJun ; Zong, ChengQing</creator><creatorcontrib>Zhang, JiaJun ; Zong, ChengQing</creatorcontrib><description>Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural networks has achieved a big breakthrough in translation performance and become the de facto paradigm of MT. This article makes a review of NMT framework, discusses the challenges in NMT, introduces some exciting recent progresses and finally looks forward to some potential future research trends.</description><identifier>ISSN: 1674-7321</identifier><identifier>EISSN: 1869-1900</identifier><identifier>DOI: 10.1007/s11431-020-1632-x</identifier><language>eng</language><publisher>Beijing: Science China Press</publisher><subject>Artificial neural networks ; Engineering ; Languages ; Machine translation ; Review</subject><ispartof>Science China. Technological sciences, 2020-10, Vol.63 (10), p.2028-2050</ispartof><rights>Science China Press and Springer-Verlag GmbH Germany, part of Springer Nature 2020</rights><rights>Science China Press and Springer-Verlag GmbH Germany, part of Springer Nature 2020.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-ef01d227bc7265b32bd277ac8abe7b36fb2948a0e4237350d7b3b231231088b73</citedby><cites>FETCH-LOGICAL-c316t-ef01d227bc7265b32bd277ac8abe7b36fb2948a0e4237350d7b3b231231088b73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11431-020-1632-x$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11431-020-1632-x$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Zhang, JiaJun</creatorcontrib><creatorcontrib>Zong, ChengQing</creatorcontrib><title>Neural machine translation: Challenges, progress and future</title><title>Science China. Technological sciences</title><addtitle>Sci. China Technol. Sci</addtitle><description>Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural networks has achieved a big breakthrough in translation performance and become the de facto paradigm of MT. This article makes a review of NMT framework, discusses the challenges in NMT, introduces some exciting recent progresses and finally looks forward to some potential future research trends.</description><subject>Artificial neural networks</subject><subject>Engineering</subject><subject>Languages</subject><subject>Machine translation</subject><subject>Review</subject><issn>1674-7321</issn><issn>1869-1900</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp1UE1LxDAQDaLgsu4P8FbwanRmkjatnmTxCxa96DkkbbrbpduuSQvrvzdLBU8OAzMM772ZeYxdItwggLoNiFIgBwKOmSB-OGEzzLOCYwFwGvtMSa4E4TlbhLCFGCIvAOWM3b-50Zs22Zly03QuGbzpQmuGpu_ukuXGtK3r1i5cJ3vfr70LITFdldTjMHp3wc5q0wa3-K1z9vn0-LF84av359flw4qXArOBuxqwIlK2VJSlVpCtSClT5sY6ZUVWWypkbsBJEkqkUMWhJYExIc-tEnN2NenGG75GFwa97UffxZWaZEoRJWQRUTihSt-H4F2t977ZGf-tEfTRJj3ZpKNN-miTPkQOTZwQsfFP_6f8P-kHLxRpRA</recordid><startdate>20201001</startdate><enddate>20201001</enddate><creator>Zhang, JiaJun</creator><creator>Zong, ChengQing</creator><general>Science China Press</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20201001</creationdate><title>Neural machine translation: Challenges, progress and future</title><author>Zhang, JiaJun ; Zong, ChengQing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-ef01d227bc7265b32bd277ac8abe7b36fb2948a0e4237350d7b3b231231088b73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Artificial neural networks</topic><topic>Engineering</topic><topic>Languages</topic><topic>Machine translation</topic><topic>Review</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, JiaJun</creatorcontrib><creatorcontrib>Zong, ChengQing</creatorcontrib><collection>CrossRef</collection><jtitle>Science China. Technological sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, JiaJun</au><au>Zong, ChengQing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Neural machine translation: Challenges, progress and future</atitle><jtitle>Science China. Technological sciences</jtitle><stitle>Sci. China Technol. Sci</stitle><date>2020-10-01</date><risdate>2020</risdate><volume>63</volume><issue>10</issue><spage>2028</spage><epage>2050</epage><pages>2028-2050</pages><issn>1674-7321</issn><eissn>1869-1900</eissn><abstract>Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural networks has achieved a big breakthrough in translation performance and become the de facto paradigm of MT. This article makes a review of NMT framework, discusses the challenges in NMT, introduces some exciting recent progresses and finally looks forward to some potential future research trends.</abstract><cop>Beijing</cop><pub>Science China Press</pub><doi>10.1007/s11431-020-1632-x</doi><tpages>23</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1674-7321
ispartof Science China. Technological sciences, 2020-10, Vol.63 (10), p.2028-2050
issn 1674-7321
1869-1900
language eng
recordid cdi_proquest_journals_2452108349
source SpringerNature Journals; Alma/SFX Local Collection
subjects Artificial neural networks
Engineering
Languages
Machine translation
Review
title Neural machine translation: Challenges, progress and future
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T17%3A14%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Neural%20machine%20translation:%20Challenges,%20progress%20and%20future&rft.jtitle=Science%20China.%20Technological%20sciences&rft.au=Zhang,%20JiaJun&rft.date=2020-10-01&rft.volume=63&rft.issue=10&rft.spage=2028&rft.epage=2050&rft.pages=2028-2050&rft.issn=1674-7321&rft.eissn=1869-1900&rft_id=info:doi/10.1007/s11431-020-1632-x&rft_dat=%3Cproquest_cross%3E2452108349%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2452108349&rft_id=info:pmid/&rfr_iscdi=true