Multilingual and Cross-cultural interactions for context-aware, and bias-controlled dialogue systems for safety-critical applications

Multilingvální a mezikulturní interakce v dialogových systémech pro bezpečnostně kritické aplikace závislé na kontextu a kontrolou zaujatosti

grant

Human computer interaction and interface, visualization and natural language, artificial intelligence, intelligence systems, multi agents systems, natural language processing, data protection and privacy, machine learning, statistical data processing and applications using data processing, formal, cognitive, functional and computational linguistics, distributed and federated adaptation of Large Language Models, Multilinguality, Multimodality, Human-in-the-loop, Bias mitigation, Grounding.

ELOQUENCE aims to research and develop new technologies supporting collaborative voice/chat bots for both low secure (low risk) and highly secure (high risk) applications. Dialogue engines powered by voice assistants have already been present in various commercial/governmental applications with lower or higher level complexities. In both cases, this complexity can be translated to a problem of analysing unstructured dialogues. Key objective of ELOQUENCE is to understand unstructured dialogues and conduct them in an explainable, safe, knowledge-grounded, trustworthy and unbiased way, while considering and building on top of prior achievements in this domain (e.g. recently launched chatGPT Large Language Models (LLMs). While including key industrial enterprises from Europe in this project (i.e. Omilia, Telefonica. ...) will approach safety with human-in-the-loop for safety-critical applications (i.e., emergency services) and via information retrieval and fact-checking against an online knowledge base for less critical autonomous systems (i.e., home-assistants). ELOQUENCE will target the R&D of these novel conversational AI technologies in multilingual and multimodal environments. Both basic research and its direct deployment through two pilots will be targeted: 1) emergency call contact centres and 2) smart assistants through decentralised training in smart homes.

Plchot Oldřich, Ing., Ph.D. (UPGM FIT VUT) , research leader
Burget Lukáš, doc. Ing., Ph.D. (UPGM FIT VUT) , team leader
Schwarz Petr, Ing., Ph.D. (UPGM FIT VUT) , team leader
Beneš Karel, Ing. (UPGM FIT VUT)
Fajčík Martin, Ing., Ph.D. (UPGM FIT VUT)
Heřmanský Hynek, prof. Ing., Dr.Eng. (UPGM FIT VUT)
Kesiraju Santosh (UPGM FIT VUT)
Peng Junyi, Msc. Eng. (UPGM FIT VUT)
Pešán Jan, Ing. (UPGM FIT VUT)
Rohdin Johan A., Dr. (UPGM FIT VUT)
Sarvaš Marek, Bc. (UPGM FIT VUT)
Sedláček Šimon, Ing. (UPGM FIT VUT)
Yusuf Bolaji (UPGM FIT VUT)