Ga verder naar de inhoud

Thomas Demeester

Currently I am an assistant professor at the Internet Technology and Data Science Lab (IDLab), Ghent University - imec, Belgium. I'm co-leading the Text-to-Knowledge research cluster with prof. Chris Develder, where we work on natural language processing (NLP) in general, for applications in several domains (the media, biomedical applications, and economics and law). Our areas of focus in NLP are information extraction, conversational agents, and representation learning in general.

Given our expertise in neural sequence modeling, we recently started looking into the use of protein language models for drug design. Give it another year before we have something decent to show here ;). My other interests include energy-based models, combining knowledge and neural networks, and synthetic data generation.

Toepassingsgebied/sector

  • Communicatie, media & telecom
  • Computerwetenschappen & IT
  • Gezondheidszorg, biomedische wetenschappen & sport

Organisatie(s)

Deep learning: van theorie tot praktijk

opleiding - Gent - UGent, UGain, VAIA

Flanders AI Research Day

evenement - Gent - Vlaams AI-onderzoeksprogramma

Deep learning: van theorie tot praktijk

opleiding - Gent - UGent, UGain, VAIA

Large Language Models en hoe ze zoekresultaten bepalen

lezing - Gent - Associatie UGent & VAIA