English

Augmenting Knowledge Graph Hierarchies Using Neural Transformers

Artificial Intelligence 2024-04-15 v1 Computation and Language Digital Libraries Information Retrieval Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2404.08020,
  title  = {Augmenting Knowledge Graph Hierarchies Using Neural Transformers},
  author = {Sanat Sharma and Mayank Poddar and Jayant Kumar and Kosta Blank and Tracy King},
  journal= {arXiv preprint arXiv:2404.08020},
  year   = {2024}
}

Comments

European Conference on Information Retrieval 2024

R2 v1 2026-06-28T15:51:44.222Z