Multilingual Machine Translation: Deep Analysis of Language-Specific Encoder-Decoders
State-of-the-art multilingual machine translation relies on a shared encoder-decoder. In this paper, we propose an alternative approach based on language-specific encoder-decoders, which can be easily extended to new languages by learning their corresponding modules. To establish a common interlingu...
Uložené v:
| Vydané v: | The Journal of artificial intelligence research Ročník 73; s. 1535 - 1552 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
San Francisco
AI Access Foundation
01.01.2022
|
| Predmet: | |
| ISSN: | 1076-9757, 1076-9757, 1943-5037 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | State-of-the-art multilingual machine translation relies on a shared encoder-decoder. In this paper, we propose an alternative approach based on language-specific encoder-decoders, which can be easily extended to new languages by learning their corresponding modules. To establish a common interlingua representation, we simultaneously train N initial languages. Our experiments show that the proposed approach improves over the shared encoder-decoder for the initial languages and when adding new languages, without the need to retrain the remaining modules. All in all, our work closes the gap between shared and language-specific encoder-decoders, advancing toward modular multilingual machine translation systems that can be flexibly extended in lifelong learning settings. |
|---|---|
| AbstractList | State-of-the-art multilingual machine translation relies on a shared encoder-decoder. In this paper, we propose an alternative approach based on language-specific encoder-decoders, which can be easily extended to new languages by learning their corresponding modules. To establish a common interlingua representation, we simultaneously train N initial languages. Our experiments show that the proposed approach improves over the shared encoder-decoder for the initial languages and when adding new languages, without the need to retrain the remaining modules. All in all, our work closes the gap between shared and language-specific encoder-decoders, advancing toward modular multilingual machine translation systems that can be flexibly extended in lifelong learning settings. |
| Author | Ruiz Costa-jussà, Marta Escolano, Carlos R. Fonollosa, José A. |
| Author_xml | – sequence: 1 givenname: Carlos surname: Escolano fullname: Escolano, Carlos – sequence: 2 givenname: Marta surname: Ruiz Costa-jussà fullname: Ruiz Costa-jussà, Marta – sequence: 3 givenname: José A. surname: R. Fonollosa fullname: R. Fonollosa, José A. |
| BookMark | eNptkMtOAjEUhhuDiYDufIAmbh3sZdoy7gjgJYG4ENZN6QVLxnZsZxa8vVxcGOPqP4vvPznnG4BeiMECcIvRCHNMH3bKpxEeYcKr6gL0MRK8qAQTvV_zFRjkvEMIVyUZ98F62dWtr33YdqqGS6U_fLBwlVTItWp9DI9wZm0DJ0HV--wzjA4u1JHe2uK9sdo7r-E86GhsKmb2lPkaXDpVZ3vzk0Owfpqvpi_F4u35dTpZFJoi3BZmM2bEYEZZaZzTzKiNNiV1ypaOcVEirjVVijI9dphQbpmhTjiMNKO8FBUdgrvz3ibFr87mVu5ilw6nZkk4E4xUlKMDRc6UTjHnZJ3Uvj091ybla4mRPOqTR30Sy5O-Q-n-T6lJ_lOl_f_4Nw_AdM0 |
| CitedBy_id | crossref_primary_10_1007_s42979_025_03719_6 crossref_primary_10_3390_electronics13163260 crossref_primary_10_26599_TST_2023_9010097 |
| ContentType | Journal Article |
| Copyright | 2022. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the associated terms available at https://www.jair.org/index.php/jair/about |
| Copyright_xml | – notice: 2022. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the associated terms available at https://www.jair.org/index.php/jair/about |
| DBID | AAYXX CITATION 8FE 8FG ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS |
| DOI | 10.1613/jair.1.12699 |
| DatabaseName | CrossRef ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest SciTech Premium Collection Technology Collection Advanced Technologies & Aerospace Collection ProQuest Central Essentials - QC ProQuest Central ProQuest Technology Collection ProQuest One ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database ProQuest Advanced Technologies & Aerospace Collection ProQuest One Academic ProQuest One Academic ProQuest Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China |
| DatabaseTitle | CrossRef Publicly Available Content Database Advanced Technologies & Aerospace Collection Computer Science Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | CrossRef Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1076-9757 1943-5037 |
| EndPage | 1552 |
| ExternalDocumentID | 10_1613_jair_1_12699 |
| GroupedDBID | .DC 29J 2WC 5GY 5VS AAKMM AAKPC AALFJ AAYFX AAYXX ACGFO ACM ADBBV ADBSK ADMLS AEFXT AEJOY AENEX AFFHD AFKRA AFWXC AKRVB ALMA_UNASSIGNED_HOLDINGS AMVHM ARAPS BCNDV BENPR BGLVJ CCPQU CITATION E3Z EBS EJD F5P FRJ FRP GROUPED_DOAJ GUFHI HCIFZ K7- KQ8 LHSKQ LPJ OK1 OVT P2P PHGZM PHGZT PIMPY PQGLB RNS TR2 XSB 8FE 8FG ABUWG AZQEC DWQXO GNUQQ JQ2 P62 PKEHL PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c301t-db852d15354dffc5dabcd43fae4f567406cc3aa35c8f1236e5d3f7f10c5364793 |
| IEDL.DBID | BENPR |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000792120900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1076-9757 |
| IngestDate | Fri Jul 25 23:45:55 EDT 2025 Tue Nov 18 22:09:27 EST 2025 Sat Nov 29 05:27:06 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c301t-db852d15354dffc5dabcd43fae4f567406cc3aa35c8f1236e5d3f7f10c5364793 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://www.proquest.com/docview/2657529360?pq-origsite=%requestingapplication% |
| PQID | 2657529360 |
| PQPubID | 5160723 |
| PageCount | 18 |
| ParticipantIDs | proquest_journals_2657529360 crossref_citationtrail_10_1613_jair_1_12699 crossref_primary_10_1613_jair_1_12699 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-01-01 |
| PublicationDateYYYYMMDD | 2022-01-01 |
| PublicationDate_xml | – month: 01 year: 2022 text: 2022-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | San Francisco |
| PublicationPlace_xml | – name: San Francisco |
| PublicationTitle | The Journal of artificial intelligence research |
| PublicationYear | 2022 |
| Publisher | AI Access Foundation |
| Publisher_xml | – name: AI Access Foundation |
| SSID | ssj0019428 |
| Score | 2.3724582 |
| Snippet | State-of-the-art multilingual machine translation relies on a shared encoder-decoder. In this paper, we propose an alternative approach based on... |
| SourceID | proquest crossref |
| SourceType | Aggregation Database Enrichment Source Index Database |
| StartPage | 1535 |
| SubjectTerms | Artificial intelligence Coders Encoders-Decoders Languages Lifelong learning Machine translation Modular systems Modules Multilingualism |
| Title | Multilingual Machine Translation: Deep Analysis of Language-Specific Encoder-Decoders |
| URI | https://www.proquest.com/docview/2657529360 |
| Volume | 73 |
| WOSCitedRecordID | wos000792120900002&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: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1076-9757 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019428 issn: 1076-9757 databaseCode: DOA dateStart: 19930101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 1076-9757 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019428 issn: 1076-9757 databaseCode: K7- dateStart: 19930101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1076-9757 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019428 issn: 1076-9757 databaseCode: BENPR dateStart: 19930101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 1076-9757 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019428 issn: 1076-9757 databaseCode: PIMPY dateStart: 19930101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3LT8IwGG8UPHgRnxFF0oOeTGGPlm5ejA-IRiCLEYOnpXRtgjEDN_Dvt-061INevGzJ9h2Wfa9-r98HwKl0PO4kLkaecAXCZMJQyBhBXJ0VMJXKGhq4puc-HQ6D8TiMbMItt22VpU00hjqZcZ0jb3u6QqB8U8e5nL8jvTVKV1ftCo11UNVIZUrOq9fdYfS4qiOE2CuG4WgHhZRQ2_qufFj7lU2zlttyvY7Bff3mlH7aZONoerX_fuI22LJHTHhVyMQOWBPpLqiV6xug1eY9MDLDt3ocfanIB6arUkDjvIoGuQt4K8QclrglcCZh36Y3kdlbL6ccdlM9FZ-hW2Hu-T4Y9bpPN3fIbllAXCn3AiWTgHiJMnwEJ1JykrAJT7AvmcCSdKhy-Jz7jPmEB1JDtQiS-JJK1-FEY8-H_gGopLNUHAIopNBlReYwijFlYTjBHg84kUSoSDjgdXBe_uaYWwhyvQnjLdahiGJKrJkSu7FhSh2crajnBfTGL3SNkh2xVcA8_uLF0d-vj8GmpycaTFalASqLbClOwAb_WEzzrGnlqWlCdXV9oEg9i-4H0csnWjDZCA |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V07T8MwED6hggQLb8QbDzAhl8S16wQJIURBVLRVJSiCKTiOLYFQWpoC4k_xG7GdhMcAGwNThnhJ7vN9Pt_ddwDb2iPSS3yKifIVpiwWOBSCYWnOCpRr4w2dXNNVi3c6wfV12B2Dt7IXxpZVlj7ROeqkL-0d-R6xGQLDTXXvcPCI7dQom10tR2jksDhXry8mZMsOmg1j3x1CTk8uj89wMVUASwPmEU7igJHEbHRGE60lS0QsE1rTQlHN6twQnJQ1IWpMBtpKkyiW1DTXvieZ1Vq34kvG5Y9TA3avAuPdZrt785G3CCnJm-94HYec8aLU3nDm3r24G1b9qk_qTmf2Cwl-5wBHbKcz_-2XzMJ0cYRGRznm52BMpfMwU46nQIW3WoCeay627fZPZnnbVY0q5Mg5LwDcRw2lBqjUZUF9jVrF9S2-GChXrYhOUtv1P8QN5Z7ZIvT-5OOWoJL2U7UMSGll06bCE5xSLsIwpkQGkmmmTKQfyBXYLc0ayUJi3U76eIhsqGVAEFkQRH7kQLACOx-rB7m0yA_r1kvzR4WDyaJP26_-_noLJs8u262o1eycr8EUsd0b7gZpHSqj4ZPagAn5PLrLhpsFlhHc_jVW3gFFWjP9 |
| 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=Multilingual+Machine+Translation%3A+Deep+Analysis+of+Language-Specific+Encoder-Decoders&rft.jtitle=The+Journal+of+artificial+intelligence+research&rft.au=Escolano%2C+Carlos&rft.au=Costa-juss%C3%A0%2C+Marta+R&rft.au=Fonollosa%2C+Jos%C3%A9+A+R&rft.date=2022-01-01&rft.pub=AI+Access+Foundation&rft.issn=1076-9757&rft.eissn=1943-5037&rft.volume=73&rft.spage=1535&rft_id=info:doi/10.1613%2Fjair.1.12699 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1076-9757&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1076-9757&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1076-9757&client=summon |