SELMA – Stream Learning for Multilingual Knowledge Transfer

Year 2021 Jan–2023 Dec
Funding European Union
Horizon 2020
Grant agreement No 957017
Partners Deutsche Welle (DW), Laboratoire Informatique d’Avignon (LIA), Priberam, Fraunhofer-Gesellschaft (FhG)
Abstract The SELMA consortium aims to build a multilingual open-source platform that can process very large volumes of content and features a continuous learning AI system. It will help media monitors and journalists make sense of huge content streams (big data analysis) and will enable them to enrich audiovisual output through transcription, translation, voice-over and subtitling, thus making it more accessible.