Aidan Hogan 

Date/Time: 04.09.2024, 11:30 

Location: D2.2.094 

Abstract 

Much has been discussed recently about how Large Language Models, Knowledge Graphs & Search Engines can be combined to address a variety of user-centric tasks. The emerging consensus is that although these technologies have many limitations, they also many synergies, and more and more technical proposals emerge in the literature on how to

combine them. However, a topic that has been in large part absent from such discussions in a research setting is the user perspective. In this talk we introduce a taxonomy of user information needs, and we use this taxonomy to study the pros, cons and possible synergies of Large Language Models, Knowledge Graphs & Search Engines in the context of these needs. We focus on the perspective of a Web user, though the discussion often generalizes straightforwardly to users in other scenarios. From this study, we sketch a road-map for future research on these topics.

Bio 

Aidan Hogan is an Associate Professor at the Department of Computer Science, University of Chile, and an Associate Researcher at the Millennium Institute for Foundational Research on Data (IMFD). He conducted his PhD research under the supervision of Prof. Axel Polleres at the National University of Ireland, Galway. Aidan's research interests relate primarily to the Semantic Web, Graph Databases, Information Extraction and Reasoning; he has published over one hundred peer-reviewed works on these topics. He is an Editor-in-Chief and Co-Founder of the journal Transactions on Graph Data & Knowledge (TGDK). He is the author of three books, the latest of which, “Knowledge Graphs”, is available online: https://kgbook.org/.