Democratizing Neural Machine Translation with OPUS-MT
2022-12-04Code Available2· sign in to hype
Jörg Tiedemann, Mikko Aulamo, Daria Bakshandaeva, Michele Boggia, Stig-Arne Grönroos, Tommi Nieminen, Alessandro Raganato, Yves Scherrer, Raul Vazquez, Sami Virpioja
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/helsinki-nlp/opus-mtOfficialIn papernone★ 790
- github.com/Helsinki-NLP/OPUS-MT-trainOfficialIn papernone★ 403
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.