skip to Main Content
ELOQUENCE – Multilingual And Cross-cultural Interactions For Context-aware, And Bias-controlled Dialogue Systems For Safety-critical Applications

ELOQUENCE is focused on the research and development of innovative technologies for collaborative voice/chatbots. Voice assistant-powered dialogue engines have previously been deployed in several commercial and governmental technological pipelines, with a diverse level of complexity. In our concept, such a complexity can be understood as a problem of analysing unstructured dialogues.

ELOQUENCE’s key objective is to better comprehend those unstructured dialogues and translate them into explainable, safe, knowledge-grounded, trustworthy and bias-controlled language models. We aim to develop a technology that can learn independently by adapting from a limited amount of data to efficiently support most of the languages spoken in the European Union. This technology will be built on a sustainable computational framework, using efficient and eco-friendly architectures. It will serve as a guide for all European citizens and reflect our European values. Additionally, it will support safety-critical applications by involving humans-in-the-loop. Overall, ELOQUENCE’s project considers building on top of and improving prior achievements in the domain of conversational agents, e.g. recently launched and public-domain Large Language Models (LLMs), such as chatGPT (e.g., more recent versions), or LaMDa most of them developed in non-EU countries. While including key industrial enterprises from Europe (i.e., Omilia, Telefonica, Synelixis).

ELOQUENCE will validate the developed technology through (i) safety-critical scenarios with human-in-the-loop for security-critical applications (i.e., emergency services in call centres) and (ii) smart home assistants via information retrieval and fact-checking against an online knowledge base for lesser risky autonomous systems (i.e., home-assistants). ELOQUENCE will target the R&D of these novel conversational AI technologies in multilingual and multimodal environments and demonstrated in several pilots.

Web:
https://cordis.europa.eu/project/id/101135916
https://eloquenceai.eu/

Funding: Horizon EUROPE

Programme:
HORIZON.2.4 – Digital, Industry and Space MAIN PROGRAMME
HORIZON.2.4.5 – Artificial Intelligence and Robotics

Topic:
HORIZON-CL4-2023-HUMAN-01-03 – Natural Language Understanding and Interaction in
Advanced Language Technologies (AI Data and Robotics Partnership) (RIA)

Funding Scheme:
HORIZON-RIA – HORIZON Research and Innovation Actions

Start date: 01/01/2024

End date: 12/31/2026

Partners: TELEFONICA INNOVACION DIGITAL SL; CONSIGLIO NAZIONALE DELLE RICERCHE; BARCELONA SUPERCOMPUTING CENTER CENTRO NACIONAL DE SUPERCOMPUTACION; FONDAZIONE BRUNO KESSLER; UNIVERZITET U NOVOM SADU FAKULTET TEHNICKIH NAUKA; EUROPEAN UNIVERSITY INSTITUTE; VYSOKE UCENI TECHNICKE V BRNE; PRIVANOVA SAS; INOSENS DOO NOVI SAD; TRANSFORMATION LIGHTHOUSE, POSLOVNO SVETOVANJE, D.O.O.; GRANTXPERT CONSULTING LIMITED; OMILIA MONOPROSOPI ETAIREIA PERIORISMENIS EFTHYNIS PAROXIS PLIROFORIKON; TILEPIKOINONIAKON KAI FONITIKON YPIRESION KAI SYSTIMATON; SYNELIXIS LYSEIS PLIROFORIKIS AUTOMATISMOU & TILEPIKOINONION ANONIMI ETAIRIA; FONDATION DE L'INSTITUT DE RECHERCHE IDIAP; BRUNEL UNIVERSITY LONDON; UNIVERSITY OF ESSEX.

Total Cost: 5,072,543.75 Euro

EU Contribution: 5,072,543.75 Euro

CNR-ICAR Cost: 450,000 Euro

CNR-ICAR EU Contribution: 450,000 Euro

Back To Top