Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our s...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2019-07 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Arivazhagan, Naveen Bapna, Ankur Firat, Orhan Lepikhin, Dmitry Johnson, Melvin Krikun, Maxim Mia Xu Chen Cao, Yuan Foster, George Cherry, Colin Macherey, Wolfgang Chen, Zhifeng Wu, Yonghui |
| description | We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that are crucial to achieving quality and practicality in universal NMT. While we prototype a high-quality universal translation system, our extensive empirical analysis exposes issues that need to be further addressed, and we suggest directions for future research. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2256350970</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2256350970</sourcerecordid><originalsourceid>FETCH-proquest_journals_22563509703</originalsourceid><addsrcrecordid>eNqNi7EKwjAUAIMgWLT_8MC5EBPbqmuxuNRJdCzBxjbl8ap9ieDf28EPcLrh7mYiUlpvkt1WqYWImXsppcpylaY6EtfKMLu3xQ9UAb1DR20wCGcbxgmVuXeOLFxGQ4zGu4HAEfjOws1hc4DSUTMtDIYaKDqDaKm1vBLzh0G28Y9LsS6Pl-KUPMfhFSz7uh_CSJOqlUozncp9LvV_1RcMp0EF</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2256350970</pqid></control><display><type>article</type><title>Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges</title><source>Free E- Journals</source><creator>Arivazhagan, Naveen ; Bapna, Ankur ; Firat, Orhan ; Lepikhin, Dmitry ; Johnson, Melvin ; Krikun, Maxim ; Mia Xu Chen ; Cao, Yuan ; Foster, George ; Cherry, Colin ; Macherey, Wolfgang ; Chen, Zhifeng ; Wu, Yonghui</creator><creatorcontrib>Arivazhagan, Naveen ; Bapna, Ankur ; Firat, Orhan ; Lepikhin, Dmitry ; Johnson, Melvin ; Krikun, Maxim ; Mia Xu Chen ; Cao, Yuan ; Foster, George ; Cherry, Colin ; Macherey, Wolfgang ; Chen, Zhifeng ; Wu, Yonghui</creatorcontrib><description>We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that are crucial to achieving quality and practicality in universal NMT. While we prototype a high-quality universal translation system, our extensive empirical analysis exposes issues that need to be further addressed, and we suggest directions for future research.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Empirical analysis ; Language translation ; Machine translation ; Multilingualism ; Translating</subject><ispartof>arXiv.org, 2019-07</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Arivazhagan, Naveen</creatorcontrib><creatorcontrib>Bapna, Ankur</creatorcontrib><creatorcontrib>Firat, Orhan</creatorcontrib><creatorcontrib>Lepikhin, Dmitry</creatorcontrib><creatorcontrib>Johnson, Melvin</creatorcontrib><creatorcontrib>Krikun, Maxim</creatorcontrib><creatorcontrib>Mia Xu Chen</creatorcontrib><creatorcontrib>Cao, Yuan</creatorcontrib><creatorcontrib>Foster, George</creatorcontrib><creatorcontrib>Cherry, Colin</creatorcontrib><creatorcontrib>Macherey, Wolfgang</creatorcontrib><creatorcontrib>Chen, Zhifeng</creatorcontrib><creatorcontrib>Wu, Yonghui</creatorcontrib><title>Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges</title><title>arXiv.org</title><description>We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that are crucial to achieving quality and practicality in universal NMT. While we prototype a high-quality universal translation system, our extensive empirical analysis exposes issues that need to be further addressed, and we suggest directions for future research.</description><subject>Empirical analysis</subject><subject>Language translation</subject><subject>Machine translation</subject><subject>Multilingualism</subject><subject>Translating</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi7EKwjAUAIMgWLT_8MC5EBPbqmuxuNRJdCzBxjbl8ap9ieDf28EPcLrh7mYiUlpvkt1WqYWImXsppcpylaY6EtfKMLu3xQ9UAb1DR20wCGcbxgmVuXeOLFxGQ4zGu4HAEfjOws1hc4DSUTMtDIYaKDqDaKm1vBLzh0G28Y9LsS6Pl-KUPMfhFSz7uh_CSJOqlUozncp9LvV_1RcMp0EF</recordid><startdate>20190711</startdate><enddate>20190711</enddate><creator>Arivazhagan, Naveen</creator><creator>Bapna, Ankur</creator><creator>Firat, Orhan</creator><creator>Lepikhin, Dmitry</creator><creator>Johnson, Melvin</creator><creator>Krikun, Maxim</creator><creator>Mia Xu Chen</creator><creator>Cao, Yuan</creator><creator>Foster, George</creator><creator>Cherry, Colin</creator><creator>Macherey, Wolfgang</creator><creator>Chen, Zhifeng</creator><creator>Wu, Yonghui</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20190711</creationdate><title>Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges</title><author>Arivazhagan, Naveen ; Bapna, Ankur ; Firat, Orhan ; Lepikhin, Dmitry ; Johnson, Melvin ; Krikun, Maxim ; Mia Xu Chen ; Cao, Yuan ; Foster, George ; Cherry, Colin ; Macherey, Wolfgang ; Chen, Zhifeng ; Wu, Yonghui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_22563509703</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Empirical analysis</topic><topic>Language translation</topic><topic>Machine translation</topic><topic>Multilingualism</topic><topic>Translating</topic><toplevel>online_resources</toplevel><creatorcontrib>Arivazhagan, Naveen</creatorcontrib><creatorcontrib>Bapna, Ankur</creatorcontrib><creatorcontrib>Firat, Orhan</creatorcontrib><creatorcontrib>Lepikhin, Dmitry</creatorcontrib><creatorcontrib>Johnson, Melvin</creatorcontrib><creatorcontrib>Krikun, Maxim</creatorcontrib><creatorcontrib>Mia Xu Chen</creatorcontrib><creatorcontrib>Cao, Yuan</creatorcontrib><creatorcontrib>Foster, George</creatorcontrib><creatorcontrib>Cherry, Colin</creatorcontrib><creatorcontrib>Macherey, Wolfgang</creatorcontrib><creatorcontrib>Chen, Zhifeng</creatorcontrib><creatorcontrib>Wu, Yonghui</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Arivazhagan, Naveen</au><au>Bapna, Ankur</au><au>Firat, Orhan</au><au>Lepikhin, Dmitry</au><au>Johnson, Melvin</au><au>Krikun, Maxim</au><au>Mia Xu Chen</au><au>Cao, Yuan</au><au>Foster, George</au><au>Cherry, Colin</au><au>Macherey, Wolfgang</au><au>Chen, Zhifeng</au><au>Wu, Yonghui</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges</atitle><jtitle>arXiv.org</jtitle><date>2019-07-11</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that are crucial to achieving quality and practicality in universal NMT. While we prototype a high-quality universal translation system, our extensive empirical analysis exposes issues that need to be further addressed, and we suggest directions for future research.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2019-07 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2256350970 |
| source | Free E- Journals |
| subjects | Empirical analysis Language translation Machine translation Multilingualism Translating |
| title | Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T10%3A41%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Massively%20Multilingual%20Neural%20Machine%20Translation%20in%20the%20Wild:%20Findings%20and%20Challenges&rft.jtitle=arXiv.org&rft.au=Arivazhagan,%20Naveen&rft.date=2019-07-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2256350970%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2256350970&rft_id=info:pmid/&rfr_iscdi=true |