Augmenting Knowledge Graph Hierarchies Using Neural Transformers
This work addresses the challenge of improving data organization and understanding in domain-specific knowledge graphs, though it appears incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of augmenting hierarchies in knowledge graphs by leveraging large language models, resulting in coverage increases of 98% for intents and 99% for colors in their knowledge graph.
Knowledge graphs are useful tools to organize, recommend and sort data. Hierarchies in knowledge graphs provide significant benefit in improving understanding and compartmentalization of the data within a knowledge graph. This work leverages large language models to generate and augment hierarchies in an existing knowledge graph. For small (<100,000 node) domain-specific KGs, we find that a combination of few-shot prompting with one-shot generation works well, while larger KG may require cyclical generation. We present techniques for augmenting hierarchies, which led to coverage increase by 98% for intents and 99% for colors in our knowledge graph.