We are proud to announce that Kairntech was selected among the winning proposals under the call of the European Defence Fund (EDF). This call received €1,031 million of EU funding.

The NEMO consortium is led by Sintef AS (Norway) and includes 12 partners from 8 different countries.

Over the course of this 5-year project the consortium will develop a state-of-the-art NLP platform for all European languages, as well as certain Eastern languages.

Each year, this platform will be subjected to a challenge organised as part of this project. This challenge measures performance (quality of results, speed, carbon footprint, etc.) and benchmarks against to two other consortia that were selected.

Generative AI and Natural Language Processing for the battlefield

The digitalization of the battlefield leads to more and more complex user interfaces and to ever-increasing volumes of language data. Language technologies such as multilingual written or spoken interactions, translations, Information Extraction and Information Retrieval are needed in an increasing number of defense systems. This applies in particular to C4ISR (Computerized Command, Control, Communications, Intelligence & Surveillance) and joint multinational and/or peacekeeping operations.

Within the NEMO consortium, Kairntech supports automatic text analysis in an efficient and practical way. The following Natural Language Processing (NLP) features will be used:

  • Named Entity Recognition (NER)
  • Text classification
  • Event detection
  • Relationship extraction
  • Question-answering (Retrieval Augmented Generation scenario – RAG).

Delivering business value for homeland security

State-of-the-art language technologies that are used in this project include GenAI, Machine Learning, Deep Learning and Large Language Models (LLMs). The extensive research will contribute to improve the compelling value proposition for homeland security partners that already use our platform.

Finally the project contributes to the creation of a European library of generic and adaptive human language technology components that offer high performances for several defence applications..