The GraphRAG Manifesto: Unlock Better GenAI Results With Knowledge Graphs | Read Now

Neo4j logo

Nodes2024

Dev Conference by Neo4j

Register for NODES 24

You only need to register once to attend all sessions.

Enhancing Knowledge Graphs with LLMs: A Novel Approach to Keyword Extraction and Synonym Merging

Session Track: Graphs

Session Time:

Session description

In this session, Andrew will guide you through his team's experience leveraging LLMs and Neo4j to uncover novel connections between Nobel Prize laureates for storytelling and interactive visualizations. In close collaboration with the Nobel Prize Outreach (NPO) organization, EQT Motherbrain researchers developed an LLM-based pipeline for keyword extraction from NPO documents and a novel method to detect and merge synonyms. They then used Neo4j to load, visualize, and inspect the generated dataset. This session will explore the methodologies, insights, and implications of leveraging LLMs in knowledge graph enhancement.

Speaker

photo of Drew McCornack

Drew McCornack

Senior ML Engineer, EQT Partners

Drew McCornack is a Senior Machine Learning Engineer at EQT Group, a position he has held since January 2022, and is based in Stockholm, Sweden. His career includes notable periods at Spotify as a Senior Data Scientist and at Amazon in various analytical and data engineering roles. Academically, Andrew has a background in Psychology with a minor in Statistics from the University of Washington.