Bio: Elena Simperl is a Professor of Computer at King’s College London and the Director of Research for the Open Data Institute (ODI). She is a Fellow of the British Computer Society and the Royal Society of Arts, and a Hans Fischer Senior Fellow. Elena’s work is at the intersection between AI and social computing. She features in the top 100 most influential scholars in knowledge engineering of the last decade and in the Women in AI 2000 ranking. She is the president of the Semantic Web Sciences Association.
Abstract: Knowledge engineering focuses on the creation and stewardship of knowledge‑based systems. As a field, it occupies a unique niche between software engineering, which involves crafting software that represents knowledge computationally, and AI, where software can reason upon knowledge representations to emulate human thought. Like many areas of knowledge work, the field is being reshaped by generative AI. This brings new opportunities to address long‑standing challenges of scale and inclusivity, while also raising concerns about accuracy, bias, and the responsible use of automation. In this talk, I will explore recent work in AI and human computer interaction that examines how to design better knowledge engineering assistants.
14:00 - 14:15
🎊 Welcome & Workshop Opening Session
14:15 - 15:05
[🎙️Keynote] Designing Better Knowledge Engineering Assistants
Prof. Elena Simperl, King's Collge London, Open Data Institute
15:05 - 15:20
[📃Presentation] A Benchmark and Field Study on the Use of LLMs and RAG for Harmonizing Job Descriptions in the Austrian Federal Administration
Nicolas Ferranti, Andreas Mild and Stefan Sobernig
15:20 - 15:35
[📃Presentation] Towards an Evaluation Framework for Generated Formal Knowledge
Maxime Haurel, Armelle Brun and Mathieu D'Aquin
15:35 - 16:00
☕ Coffee Break
16:00 - 16:15
[📃Presentation] LLM Driven Justified Alignment
Diego Conde Herreros, George Hannah, Terry Payne, Jacopo de Berardinis, Valentina Tamma, David Chaves-Fraga and Oscar Corcho
16:15 - 16:30
[📃Presentation] Understanding the Gap in Evaluation Frameworks and Metrics for RAG-based Question-Answering System
Nakul Mehta, Adegboyega Ojo and Edward Curry
16:30 - 16:45
[📃Presentation] Ontology Reuse in LLMs Generated Ontologies: A Comparative Evaluation Framework
Henon Mengistu Lamboro, Amel Bouzeghoub, Cécile Rabrait, Antonio Kung, Olivier Genest and Amélie Gyrard
16:45 - 17:00
[📃Presentation] Evaluating LLMs in Ontology Transformation: Study on Property Chain Shortcutting
Kateřina Haniková, Vojtěch Svátek and Ondřej Zamazal
17:00 - 17:15
[📃Presentation] T2S-Metrics: Unified Library for Evaluating SPARQL Queries Generated From Natural Language
Yousouf Taghzouti, Tao Jiang, Camille Juigné, Benjamin Navet, Fabien Gandon, Franck Michel and Louis Felix Nothias
17:15 - 17:30
💬 Discussion & Feedback Session
Hotel Dubrovnik Palace
Dubrovnik, Croatia