Skip to main content

Lifelong UNiversal lAnguage Representation

Project description

Deep learning algorithms to improve machine translation

Machine translation is automated translation performed by a computer with no human involvement. Despite technological advances and the highly multilingual nature of our world, speech and language technology has not kept up with demands in all languages. The EU-funded LUNAR project will develop a multilingual and multimodal model that builds upon a lifelong universal language representation. This model will compensate for the lack of supervised data and significantly increase the system capacity of generalisation. It will reduce the number of required translation systems from quadratic to linear as well as allow for an incremental adaptation of new languages and data.

Call for proposal

ERC-2020-STG
See other projects for this call

Host institution

UNIVERSITAT POLITECNICA DE CATALUNYA
Address
Calle Jordi Girona 31
08034 Barcelona
Spain
Activity type
Higher or Secondary Education Establishments
EU contribution
€ 1 498 723

Beneficiaries (1)

UNIVERSITAT POLITECNICA DE CATALUNYA
Spain
EU contribution
€ 1 498 723
Address
Calle Jordi Girona 31
08034 Barcelona
Activity type
Higher or Secondary Education Establishments