Talking to Machines: do you read me?

Lina Maria Rojas-Barahona

Abstract: In this dissertation I would like to guide the reader to the research on dialogue but more precisely the research I have conducted during my career since my PhD thesis. Starting from modular architectures with machine learning/deep learning and reinforcement learning to end-to-end deep neural networks. Besides my work as research associate, I also present the work I have supervised in the last years. I proposed four PhD thesis Conventions industrielles de formation par la recherche (CIFRE) that Orange accepted to fund. Therefore, I could co-supervise four PhD candidates: Timothy Garwood supervised by Claire Gardent at CNRS, Thibault Cordier supervised by Fabrice Lefevre at the University of Avignon, Sebastien Montella supervised by Alexis Nasr at the university of Aix-Marseille, Léo Jacqmin supervised by Benoit Favre at the University of Aix-Marseille. For 5 years I was head of the industrial research project on dialogue, DIalogue in NAtural Language (DIANA), which gave me the opportunity of supervising the work of the young researcher Quentin Brabant, other experimented researchers, a developer as well as students in internship and apprenticeship. Particularly, I present the work of Thibault Cordier, Sebastien Montella and Quentin Brabant. Finally, I present the scientific project, where I discuss about Large Language Models (LLMs) for Task-Oriented Dialogue and Multimodal Task-Oriented Dialogue.