Institute of Formal and Applied Linguistics
Charles University, Czech Republic
Faculty of Mathematics and Physics
Towards Natural Behaviour of Dialogue Systems with Explicit Dialogue Control
The goal of dialogue system researchers has always been to create artefacts that offer natural interaction capabilities and effortlessly communication by means that humans also use to communicate among themselves. Even though systems like ChatGPT are already very good in form and style, there are more things to natural dialogue system behaviour than these LLM-based agents are capable of. I believe that this requires additional control capabilities of a dialogue system. In this talk, I will motivate this with insights from an analysis of communication styles in dialogues. I will continue with work on learning an explicit dialogue control component through reinforcement learning by optimizing on the estimated user satisfaction and thus ultimately improving the perceived naturalness of the interaction. I will finish with arguing that this basic idea is still relevant in the age of LLMs.
*** The talk will be delivered in person (MFF UK, Malostranské nám. 25, 4th floor, room S1) and will be streamed via Zoom. For details how to join the Zoom meeting, please write to sevcikova et ufal.mff.cuni.cz ***
Stefan Ultes is a full professor of natural language generation and dialogue Systems at the Otto-Friedrich-University of Bamberg, Germany, and a member of the executive board of the Bamberg Center for Artificial Intelligence (BaCAI). Previously, he was leading the speech technology research group at Mercedes Benz Research & Development in Sindelfingen, Germany, and a research associate at the spoken dialogue systems group at the University of Cambridge, UK. He has received his diploma (master equivalent) in computer science from the Karlsruhe Institute of Technology, Germany, in 2010 and his doctorate (PhD) on “User-centred Adaptive Spoken Dialogue Modelling” at the dialogue systems group at Ulm University, Germany, in 2015. His research interests focus on natural language processing and dialogue systems, especially on enabling natural spoken interaction between humans and machines through dialogue. He has co-authored over 100 peer-reviewed publications, regularly serves under different roles in the ACL and SIGDIAL community, and has been a co-organizer of multiple international conferences and workshops.