logo
ProjectEnded

Lifelong UNiversal lAnguage Representation

Ended · Spain

Source: EU Funding & Tenders Portal

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 de

Status
Closed
Sector
Government
Location
Spain
Updated
22 Jul 2026
Source
EU Funding & Tenders Portal

ConstructChat

Ask ConstructChat about Lifelong UNiversal lAnguage Representation

Pick a question to edit it, or write your own.

First answer free · no account

I am a

Project Information FAQ

Project Information

4 Q
The project “Lifelong UNiversal lAnguage Representation” is an infrastructure initiative in the Government sector, located in Spain. Taiyo aggregates data on it from EU Funding & Tenders Portal.

Participants

Sponsoring Agency

Status

Original status

ended

Taiyo status

Closed

Taiyo last update

2026-07-22

Contact

Not available for this record.

Description

Description

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.

Location

Country

Spain

Source

Source

EU Funding & Tenders Portal

URL

More Details

Record type

Project

Sector

Government

Article published date

2026-02-15

More on this project

Research

Free account

View all details

You are reading the public part. A free account opens the rest:

  • Every detail on this project
  • News and media coverage
  • Technical research
View all details

Free account · no card · lands you back on this project