The First International Workshop on Argumentation and Applications
Keynote speaker
Prof. Antonis Kakas, University of Cyprus
Antonis C. Kakas is a Professor at the Department of Computer Science of the University of Cyprus. He obtained his Ph.D. in Theoretical Physics from Imperial College London in 1984. His interest in Computing and AI started in 1989 under the group of Professor Kowalski. Since then his research has concentrated on computational logic in AI with particular interest in argumentation, abduction and induction and their application to machine learning and cognitive systems. Currently, he is working on the development of a new framework of Cognitive Programming that aims to offer an environment for developing Human-centric AI systems that can be naturally used by developers and human users at large. He is the National Contact Point for Cyprus in the flagship EU project on AI, AI4EU. He has recently co-founded a start-up company in Paris, called Argument Theory, which offers solutions to real-life application decision taking problems based on argumentation technology.
- Title: The Practical side of Argumentation
- Abstract: Computational Argumentation has been extensively studied over the last decades reaching a mature theoretical understanding of the field. To turn this into real-life practice we need to face two major challenges. On the one hand we need to address the (usual) knowledge acquisition problem that the development of any real-life application requires. In general terms, this means that either we need to have automated frameworks that would allow the translation of requirements from natural Language into machine readable forms of knowledge of argumentation and/or we need to have machine learning processes that would automatically learn knowledge in argumentation form. On the other hand, argumentation needs to live up to its promised potential of cognitive compatibility with human reasoning. In particular, we need to develop the argumentation technology to produce cognitive explanations that are naturally grounded in the vocabulary and the current context of the application problem.
The talk will show how these challenges manifest themselves in a variety of different application domains, such as medical decision support, personal cognitive assistants and policy compliance. It will analyze these challenges and present concrete ways in which they can be addressed, including ways that leverage the link of argumentation with the technology of Large Language Models.