Keynote Speaker: Prof.Dr. Piek Th.J.M. Vossen

Title: Developing Dutch Language Models and Conversational AI for monitoring functioning and wellbeing

Abstract: In this talk I will describe how we developed a Dutch Large Language Model from millions of medical notes and fine-tuned the model to track the functional level of patients over time according to the WHO International classification of functioning (ICF). I will also present our recent work to build a conversational AI that can monitor patients and elderly people through direct social interaction.

Bio: I am a Professor in Computational Lexicology at the Vrije Universiteit Amsterdam. Machines that understand language are my passion. After 10 years in industry, I became full professor (2009) and established the Computational Linguistics and Text Mining Lab, where 25 researchers study language models. I supervised 20 PhDs and 10 postdocs and developed two master programmes. My groundwork on cross-language conceptual modelling and interoperability led me to found the Global-WordNet-Association (GWA) for building WordNets in languages and connecting these through semantic graphs (2001). GWA addresses fundamental questions at scale: what words we use, what they stand for, and how they relate. I developed Dutch WordNet databases. Today, WordNet reminisces in large language models (LLM) that automatically place words in semantic graphs. I built an LLM from Dutch medical notes with AUMC researchers for medical text classification. I coordinated numerous programmes creating news reading machines to reconstruct what happened in the world as event-centric knowledge graphs. In my Spinoza-financed programme, I studied three foundations for language understanding: identity, reference, and perspective, resulting in the GraSP model as the “theory-of-mind” of robots communicating with people within the Hybrid Intelligence gravitation programme.