Skip to main content
European Commission logo print header

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.

Objective

Why is machine translation between English and Portuguese significantly better than machine translation between Dutch and Spanish? Why do speech recognizers work better in German than Finnish? The main problem is the insufficient amount of labelled data for training in both cases. Although the world is multimodal and highly multilingual, speech and language technology is not keeping up with the demand in all languages. We need better learning methods that exploit the advancements of a few modalities and languages for the benefit of others. This proposal addresses the low-resources problem and the expensive approach to multilingual machine translation since systems for all translation pairs are required.
LUNAR proposes to jointly learn 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 generalization from training data given the unconventional variety of employed resources. This model will reduce the number of required translation systems from quadratic to linear as well as allowing for an incremental adaptation of new languages and data.
The high-risk/high-gain relies on automatically training a universal language representation by specifically designed deep learning algorithms. LUNAR will employ an encoder-decoder architecture. The encoder represents an abstraction of the input by reducing its dimensionality,which will become the proposed universal language representation; from this abstraction, the decoder generates the output. The encoder-decoder internal architecture will be designed for learning the universal language representation,which will be appropriately integrated as an objective of the architecture.
LUNAR will impact multidisciplinary communities of specialists in computer science, mathematics, engineering and linguistics who work on natural language understanding and speech processing applications.

Coordinator

UNIVERSITAT POLITECNICA DE CATALUNYA
Net EU contribution
€ 1 498 723,00
Address
Calle jordi girona 31
08034 Barcelona
Spain

See on map

Region
Este Cataluña Barcelona
Activity type
Higher or Secondary Education Establishments
Links
Other funding
€ 0,00

Beneficiaries (1)