Tuesday 10.12.2024 – Semantic Data Modeling and Knowledge Graphs in the era of Large Language Models – Panos Alexopoulos

on Tuesday 10 December at 14:50 (2:50 PM) Helsinki time. Teams meeting.

Tiistaina 10.12. klo 14:50 (Teams lobby) 15:00 tapahtumaohjelma alkaa –

Linkki lähetetään ilmoittautuneille ennen tapahtumaa. Link to be sent to registered participants before the event.

15:00 (Helsinki time) – Panos Alexopoulos

Panos Alexopoulos – Semantic Data Modeling and Knowledge Graphs in the era of Large Language Models – Opportunities and Challenges.

In an era dominated by the capabilities of Large Language Models (LLMs), the role of traditional semantic data modeling and knowledge engineering faces a transformative moment. While LLMs are proficient in processing and generating natural language at scale, the structured, interconnected approach of ontologies and knowledge graphs remains critical for managing complex, entity-rich data. This talk will explore the evolving interplay between LLMs and knowledge graphs, emphasizing how each can complement the other: LLMs can enhance knowledge graph development by assisting in schema design, knowledge extraction, and quality assurance, while knowledge graphs offer LLMs a foundation to improve accuracy and reduce hallucinations. We will examine both the opportunities and challenges of this synergy, outlining practical strategies for getting the best of the two worlds.

With Large Language Models (LLMs) advancing rapidly, the role of traditional semantic data modeling and knowledge engineering is at a pivotal point. LLMs excel at large-scale language processing and generation, but structured frameworks like ontologies and knowledge graphs are still essential for managing complex, entity-rich data. This talk dives into the practical intersections between LLMs and knowledge graphs, showing how each can strengthen the other: LLMs can streamline schema design, automate knowledge extraction, and support quality control in knowledge graphs, while knowledge graphs can help LLMs improve reliability and minimize hallucinations. We’ll cover the key opportunities and challenges and lay out practical strategies for effectively integrating these approaches.

Panos Alexopoulos has been working since 2006 at the intersection of data, semantics and software, contributing in building intelligent systems that deliver value to business and society. Born and raised in Athens, Greece, Panos currently works as a principal educator at OWLTECH, developing and delivering training workshops that provide actionable knowledge and insights for data and AI practitioners. He also works as Head of Ontology at Textkernel BV, in Amsterdam, Netherlands, leading a team of data professionals in developing and delivering a large cross-lingual Knowledge Graph in the HR and Recruitment domain.

Panos has published several papers at international conferences, journals and books, and he is a regular speaker in both academic and industry venues. He is also the author of the O’Reilly book “Semantic Modeling for Data – Avoiding Pitfalls and Dilemmas”, a practical and pragmatic field guide for data practitioners that want to learn how semantic data modeling is applied in the real world.

– tapahtumamme päättyy viimeistään 16:30. Our event ends at about 4:30 pm Helsinki time.

Registrations by e-mail: info@tdwi.fi. Mikäli et vielä ole yhdistyksen jäsen, mutta haluat liittyä ja samalla ilmoittautua tilaisuuteen: info@tdwi.fi

Tervetuloa! Welcome!

Petri Hakanen, puheenjohtaja