Natural Language Interface for Goal-Oriented Knowledge Graphs Using Retrieval-Augmented Generation

Kosuke Yano, Yoshinobu Kitamura, Kazuhiro Kuwabara

2025

Abstract

A search method leveraging Retrieval-Augmented Generation (RAG) for goal-oriented knowledge graphs is proposed, with a specific focus on function decomposition trees. A function decomposition tree represents hierarchically functions of artifacts or actions of human with explicit descriptions of purposes and goals. We developed a schema to convert the trees into RDF, enabling structured and efficient searches. Through RAG technology, a natural language interface converts user’s inputs into SPARQL queries, retrieving relevant data and subsequently presenting them in an accessible and chat-based format. Such a flexible, and purpose-driven searches enhance usability in complex knowledge graphs. We demonstrate the tool effectively retrieves actions, intentions, and dependencies using an illustrative and a real-world example of function decomposition trees.

Paper Citation

in Harvard Style

Yano K., Kitamura Y. and Kuwabara K. (2025). Natural Language Interface for Goal-Oriented Knowledge Graphs Using Retrieval-Augmented Generation. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 975-982. DOI: 10.5220/0013245700003890

in Bibtex Style

@conference{icaart25,
author={Kosuke Yano and Yoshinobu Kitamura and Kazuhiro Kuwabara},
title={Natural Language Interface for Goal-Oriented Knowledge Graphs Using Retrieval-Augmented Generation},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={975-982},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013245700003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Natural Language Interface for Goal-Oriented Knowledge Graphs Using Retrieval-Augmented Generation
SN - 978-989-758-737-5
AU - Yano K.
AU - Kitamura Y.
AU - Kuwabara K.
PY - 2025
SP - 975
EP - 982
DO - 10.5220/0013245700003890
PB - SciTePress