Discover great EU-funded Innovations
Highly scalable SELMA NLP orchestration platform for processing extreme data volumes
Market Maturity: Tech Ready
These are innovations that are progressing on technology development process (e.g. pilots, prototypes, demonstration). Learn more
Market Creation Potential
This innovation was assessed by the JRC’s Market Creation Potential indicator framework as addressing the needs of existing markets and existing customers. Learn more
Women-led innovation
A woman had a leadership role in developing this innovation in at least one of the Key Innovator organisations listed below.
Go to Market needs
Needs that, if addressed, can increase the chances this innovation gets to (or closer to) the market incude:
  • Prepare for Market entry
Location of Key Innovators developing this innovation
Key Innovators
UN Sustainable Development Goals(SDG)
This innovation contributes to the following SDG(s)
Strengthen the means of implementations and revitalize the global partnership for sustainable development

The UN explains: "A successful sustainable development agenda requires partnerships between governments, the private sector and civil society. These inclusive partnerships built upon principles and values, a shared vision, and shared goals that place people and the planet at the centre, are needed at the global, regional, national and local level."

The EU-funded Research Project
This innovation was developed under the Horizon 2020 project SELMA with an end date of 31/12/2023
  • Read more about this project on CORDIS
Description of Project SELMA
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.

Innnovation Radar's analysis of this innovation is based on data collected on 13/09/2022.
The unique id of this innovation in the European Commission's IT systems is: 109404