research projects


MT4All: Unsupervised MT for low-resourced language pairs
(2020 - 2021)

The MT4All CEF action aims to provide bilingual resources (bilingual dictionaries and machine translation systems) for the under-resourced languages in fields of public interest at the EU level, such as e-Health and e-Justice. Based on monolingual data, MT4All will apply the last advances in unsupervised machine translation to derive bilingual dictionaries and translation models. The new bilingual resources will be use to enhance existing machine-translation engines of the CEF Automated Translation Building block, and to build new engines for non-covered language pairs or domains.
Organization:  European Comission
Main researcher: Gorka Labaka
Participants
Eneko Agirre, Nora Aranberri, Iakes Goenaga, Uxoa Iñurrieta, Gorka Labaka, Olatz Perez de Viñaspre, German Rigau


More projects