Skip to main content

Stream Learning for Multilingual Knowledge Transfer

Objective

SELMA builds a continuous deep learning multilingual media platform using extreme analytics.

Large amounts of multilingual text and speech data are available in the internet, but the potential to fully take advantage of this data has remained largely untapped. Recent advances in deep learning and transfer learning have opened the door to new possibilities – in particular integrating knowledge from these large unannotated datasets into plugable models for tackling machine learning tasks.

The aim of the Stream Learning for Multilingual Knowledge Transfer (SELMA) is to address three tasks: ingest large amounts of data and continuously train machine learning models for several natural language tasks; monitor these data streams using such models to improve multilingual Media Monitoring (use case 1); and improve the task of multilingual News Content Production (use case 2), thereby closing the loop between content monitoring and production.

SELMA has eight goals: 1. Enable processing of massive video and text data streams in a distributed and scalable fashion 2. Develop new methods for training unsupervised deep learning language models in 30 languages 3. Enable knowledge transfer across tasks and languages, supporting low-resourced languages 4. Develop novel data analytics methods and visualizations to facilitate the media monitoring decision-making process 5. Develop an open-source platform to optimize multilingual content production in 30 languages 6. Fine-tune deep learning models from user feedback, reducing recurring errors 7. Ensure a sustainable exploitation of the SELMA platform 8. Encourage active user involvement in the platform.

Achieving these aims requires advancing the state of the art in multiple technologies (transfer learning, language modelling, speech recognition, machine translation, summarization, speech synthesis, named entity linking, learning from user feedback), while building upon previous project results and existing services.

Field of science

  • /humanities/languages and literature/linguistics/phonetics
  • /natural sciences/computer and information sciences/artificial intelligence/machine learning/transfer learning
  • /humanities/languages and literature/languages - general
  • /natural sciences/computer and information sciences/artificial intelligence/machine learning/deep learning
  • /natural sciences/computer and information sciences/data science/data analysis

Call for proposal

H2020-ICT-2020-1
See other projects for this call

Funding Scheme

RIA - Research and Innovation action

Coordinator

DEUTSCHE WELLE
Address
Kurt Schumacher Strasse 3
53113 Bonn
Germany
Activity type
Public bodies (excluding Research Organisations and Secondary or Higher Education Establishments)
EU contribution
€ 821 812,50

Participants (4)

AVIGNON UNIVERSITE
France
EU contribution
€ 599 281,25
Address
Rue Louis Pasteur 74
84029 Avignon Cedex 01
Activity type
Higher or Secondary Education Establishments
LATVIJAS UNIVERSITATES MATEMATIKAS UN INFORMATIKAS INSTITUTS
Latvia
EU contribution
€ 576 250
Address
Raina Bulvaris 29
1459 Riga
Activity type
Research Organisations
PRIBERAM INFORMATICA SA
Portugal
EU contribution
€ 749 412,50
Address
Alameda D Afonso Henriques 41 2
1000-123 Lisboa
Activity type
Private for-profit entities (excluding Higher or Secondary Education Establishments)
FRAUNHOFER GESELLSCHAFT ZUR FOERDERUNG DER ANGEWANDTEN FORSCHUNG E.V.
Germany
EU contribution
€ 705 750
Address
Hansastrasse 27C
80686 Munchen
Activity type
Research Organisations