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, Sámi Virpioja
Abstract
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.
Topics & Concepts
Machine translationOpusModular designComputer scienceTranslation (biology)Computer-assisted translationWorkflowFocus (optics)Quality (philosophy)Artificial intelligenceSoftware engineeringProgramming languageOperating systemDatabaseEpistemologyPhilosophyMessenger RNAOpticsBiochemistryGeneChemistryPhysicsNatural Language Processing TechniquesTopic ModelingMultimodal Machine Learning Applications