When data outgrows what a human team can process, AI is most useful as infrastructure: turning unstructured text into structured, computable forms that support automated processing and reasoning at scale.

In this session, we’ll share how the team at Leicester built that infrastructure, from schema-based extraction to knowledge graphs and machine-readable rules, and what it costs them along the way.

Speaker

Yunze Wang (Patrick)
Research Software Engineer, University of Leicester

What to expect

• Structured extraction – pulling information from supplied text into defined schemas, backed by use cases.
• Knowledge graphs from text – building knowledge graphs from input text and tackling challenges and solutions, including entity resolution, relationship enrichment, and indexing resolution, relationship enrichment and indexing.
• Normative knowledge graphs (constraints) – extraction of use conditions, contracts, requirements, etc. and scalable reasoning on the extracted format, backed by our solutions.
• Lessons learned – the lessons, pitfalls, costs and efficiency compromises we learned from the process.

Who is this for

Teams and researchers who generate, manage or consume data in large quantities and want to explore AI-assisted automation and reasoning at scale.

How to join

This event will be held virtually. Register to join the ELIXIR-UK RDM Club to receive the meeting link and further details. If you don't wish to attend the community calls in the future, you can unsubscribe at any time.