Integrating Conversational Agents and Knowledge Graphs Within the Scholarly Domain 

The Problem: 

Large language models (LLMs) have revolutionised question answering, including within the scientific domain. However, scientific question-answering remains significantly challenging for the current generation of LLMs due to their reliance on highly specialised concepts.   

A promising solution:  

Time to have some lunch and visit the exhibition. See you back at 14:20 for the start of the afternoon sessions!

Ofcom, the independent communications regulator in the UK, is tasked with implementing the Online Safety Act, which was passed by Parliament in October 2023. This groundbreaking legislation represents a significant shift in how online platforms are regulated, placing greater responsibility on online services, including social media platforms, search engines, pornography sites, messaging apps, gambling and gaming platforms, to proactively ensure a safe and secure online environment for all users, particularly children. 

Like many organisations AstraZeneca R&D faces the challenge of siloed data. We see adopting Findable, Accessible, Interoperable, Re-usable (FAIR) Data principles as a route to releasing value from our existing data as well as setting us up to be able to do so much more with new data we generate from here on. Semantic knowledge graphs are a proven approach to achieving this and we started by building Scientific Intelligence, a knowledge graph to support exploration and analysis of clinical data.  

The objective: to build a robust knowledge graph that supports a large-scale customer facing question-answering system.  

Context: Empirical experience from the presenter’s work supporting question-answering functionality in virtual assistants (notably Amazon Alexa) and, more recent, work at Compare the Market.  

Covering: The talk will cover common pitfalls and proven solutions, including insights into what works - and what doesn’t - when deploying and scaling knowledge graphs in real-world environments. 

Your chance to visit the DAM Europe and Semantic Data exhibition and network with fellow attendees - co-located with DAM Europe.

What’s been done up to now:

The challenges, solutions and what we learned along the way 

Context: 

The IKEA Knowledge Graph (IKG) is central to digital transformation across the IKEA value chain. It enriches customer experiences both online and offline. 

Lead Ontologist Christelle Maignan describes how the IKG is bridging the gap between physical and digital customer experiences. 

What’s already being deployed: 

Enjoy breakfast and explore the DAM Europe and Semantic Data co-located exhibition before joining the event!