Democratizing Neural Machine Translation with OPUS-MT
Authors:
- Jörg TiedemannJTJörg Tiedemann
- Mikko AulamoMAMikko Aulamo
- Daria BakshandaevaDBDaria Bakshandaeva
- Michele BoggiaMBMichele Boggia
- Stig-Arne GrönroosSGStig-Arne Grönroos
- Tommi NieminenTNTommi Nieminen
- Alessandro RaganatoARAlessandro Raganato
- Yves ScherrerYSYves Scherrer
- Raul VazquezRVRaul Vazquez
- Sami VirpiojaSVSami Virpioja
Preprint
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 on-going mission of increasing language coverage and translation quality, and also describe on-going work on the development of modular translation models and speed-optimized compact solutions for real-time translation on regular desktops and small devices.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine TranslationTransactions of the Association for Computational Linguistics, 2022
- A Systematic Study of Inner-Attention-Based Sentence Representations in Multilingual Neural Machine TranslationComputational Linguistics, 2020
- Quantifying the Effect of Machine Translation in a High-Quality Human Translation Production ProcessInformatics, 2020
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot TranslationTransactions of the Association for Computational Linguistics, 2017
- A Linguistic Evaluation of Rule-Based, Phrase-Based, and Neural MT EnginesThe Prague Bulletin of Mathematical Linguistics, 2017
- Efficient Word Alignment with Markov Chain Monte CarloThe Prague Bulletin of Mathematical Linguistics, 2016
- BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic networkArtificial Intelligence, 2012
- On Growing and Pruning Kneser–Ney Smoothed $ N$-Gram ModelsIEEE Transactions on Audio, Speech, and Language Processing, 2007
- Translations as semantic mirrors: from parallel corpus to wordnet2004
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955