Democratizing neural machine translation with OPUS-MT

Jörg Tiedemann; Mikko Aulamo; Daria Bakshandaeva; Michele Boggia; Stig Arne Grönroos; Tommi Nieminen; Alessandro Raganato; Yves Scherrer; Raúl Vázquez; Sami Virpioja

doi:10.1007/s10579-023-09704-w

Democratizing neural machine translation with OPUS-MT

Jörg Tiedemann, Mikko Aulamo, Daria Bakshandaeva, Michele Boggia, Stig Arne Grönroos, Tommi Nieminen, Alessandro Raganato, Yves Scherrer, Raúl Vázquez, Sami Virpioja

Tutkimustuotos: Artikkelijulkaisu › Artikkeli › Tieteellinen › vertaisarvioitu

Abstrakti

This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows. We discuss our ongoing mission of increasing language coverage and translation quality, and also describe work on the development of modular translation models and speed-optimized compact solutions for real-time translation on regular desktops and small devices.

Alkuperäiskieli	englanti
Lehti	Language Resources and Evaluation
Sivumäärä	43
ISSN	1574-020X
DOI - pysyväislinkit	https://doi.org/10.1007/s10579-023-09704-w
Tila	Julkaistu - 13 jouluk. 2023
OKM-julkaisutyyppi	A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä, vertaisarvioitu

Lisätietoja

Publisher Copyright:
© 2023, The Author(s).

Tieteenalat

6121 Kielitieteet
113 Tietojenkäsittely- ja informaatiotieteet

Pääsy asiakirjaan

10.1007/s10579-023-09704-wLisenssi: CC BY

s10579-023-09704-wLopullinen julkaistu versio, 3,33 MBLisenssi: CC BY

2 Päättynyt
3 Aktiivinen

GreenNLP: GreenNLP - Att kontrollera koldioxidavtrycket inom hållbar språkteknologi
Tiedemann, J. (Projektinjohtaja), Attieh, J. (osallistuja), Nieminen, T. J. (osallistuja) & Štefánik, M. (osallistuja)
Suomen Akatemia Projektilaskutus
01/01/2023 → 31/12/2025
Projekti: Suomen Akatemia: : Suunnattu akatemiahanke
High Performance Language Technologies
Tiedemann, J. (Projektinjohtaja), Aulamo, M. (osallistuja), De Gibert Bonet, O. (osallistuja), Grönroos, S.-A. (osallistuja), Ji, S. (osallistuja), Mickus, T. (osallistuja), Vahtola, T. (osallistuja), Vazquez , R. (osallistuja) & Virpioja, S. P. (osallistuja)
Charles University in Prague Faculty of Science Department of Teaching and Didactics of Biology
01/09/2022 → 31/08/2025
Projekti: EU Horizon Europe: Innovation actions (HORIZON-IA)
OPUS: The Open Parallel Corpus
Tiedemann, J. (Projektinjohtaja)
01/06/2004 → …
Projekti: Tutkimusprojekti

Siteeraa tätä

@article{ea77f4fe7c9a451c9c9d4fb4fbf43212,

title = "Democratizing neural machine translation with OPUS-MT",

abstract = "This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows. We discuss our ongoing mission of increasing language coverage and translation quality, and also describe work on the development of modular translation models and speed-optimized compact solutions for real-time translation on regular desktops and small devices.",

keywords = "Computer-assisted translation, Neural machine translation, Open source, Parallel corpora, 6121 Languages, 113 Computer and information sciences",

author = "J{\"o}rg Tiedemann and Mikko Aulamo and Daria Bakshandaeva and Michele Boggia and Gr{\"o}nroos, {Stig Arne} and Tommi Nieminen and Alessandro Raganato and Yves Scherrer and Ra{\'u}l V{\'a}zquez and Sami Virpioja",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

day = "13",

doi = "10.1007/s10579-023-09704-w",

language = "English",

journal = "Language Resources and Evaluation",

issn = "1574-020X",

publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Democratizing neural machine translation with OPUS-MT

AU - Tiedemann, Jörg

AU - Aulamo, Mikko

AU - Bakshandaeva, Daria

AU - Boggia, Michele

AU - Grönroos, Stig Arne

AU - Nieminen, Tommi

AU - Raganato, Alessandro

AU - Scherrer, Yves

AU - Vázquez, Raúl

AU - Virpioja, Sami

PY - 2023/12/13

Y1 - 2023/12/13

N2 - This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows. We discuss our ongoing mission of increasing language coverage and translation quality, and also describe work on the development of modular translation models and speed-optimized compact solutions for real-time translation on regular desktops and small devices.

AB - This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows. We discuss our ongoing mission of increasing language coverage and translation quality, and also describe work on the development of modular translation models and speed-optimized compact solutions for real-time translation on regular desktops and small devices.

KW - Computer-assisted translation

KW - Neural machine translation

KW - Open source

KW - Parallel corpora

KW - 6121 Languages

KW - 113 Computer and information sciences

U2 - 10.1007/s10579-023-09704-w

DO - 10.1007/s10579-023-09704-w

M3 - Article

AN - SCOPUS:85179733880

SN - 1574-020X

JO - Language Resources and Evaluation

JF - Language Resources and Evaluation

ER -

Democratizing neural machine translation with OPUS-MT

Abstrakti

Lisätietoja

Tieteenalat

Pääsy asiakirjaan

Projektit

GreenNLP: GreenNLP - Att kontrollera koldioxidavtrycket inom hållbar språkteknologi

High Performance Language Technologies

OPUS: The Open Parallel Corpus

Siteeraa tätä