Augmenting Knowledge Graph Hierarchies Using Neural Transformers

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sharma, Sanat, Poddar, Mayank, Kumar, Jayant, Blank, Kosta, King, Tracy
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916202349068288
author Sharma, Sanat
Poddar, Mayank
Kumar, Jayant
Blank, Kosta
King, Tracy
author_facet Sharma, Sanat
Poddar, Mayank
Kumar, Jayant
Blank, Kosta
King, Tracy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_08020
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Augmenting Knowledge Graph Hierarchies Using Neural Transformers
Sharma, Sanat
Poddar, Mayank
Kumar, Jayant
Blank, Kosta
King, Tracy
Artificial Intelligence
Computation and Language
Digital Libraries
Information Retrieval
Machine Learning
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.
title Augmenting Knowledge Graph Hierarchies Using Neural Transformers
topic Artificial Intelligence
Computation and Language
Digital Libraries
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2404.08020