Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schema

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Xiaohan, Wu, Xixin, Meng, Helen
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917881302745088
author Feng, Xiaohan
Wu, Xixin
Meng, Helen
author_facet Feng, Xiaohan
Wu, Xixin
Meng, Helen
contents We propose an ontology-grounded approach to Knowledge Graph (KG) construction using Large Language Models (LLMs) on a knowledge base. An ontology is authored by generating Competency Questions (CQ) on knowledge base to discover knowledge scope, extracting relations from CQs, and attempt to replace equivalent relations by their counterpart in Wikidata. To ensure consistency and interpretability in the resulting KG, we ground generation of KG with the authored ontology based on extracted relations. Evaluation on benchmark datasets demonstrates competitive performance in knowledge graph construction task. Our work presents a promising direction for scalable KG construction pipeline with minimal human intervention, that yields high quality and human-interpretable KGs, which are interoperable with Wikidata semantics for potential knowledge base expansion.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schema
Feng, Xiaohan
Wu, Xixin
Meng, Helen
Artificial Intelligence
Information Retrieval
We propose an ontology-grounded approach to Knowledge Graph (KG) construction using Large Language Models (LLMs) on a knowledge base. An ontology is authored by generating Competency Questions (CQ) on knowledge base to discover knowledge scope, extracting relations from CQs, and attempt to replace equivalent relations by their counterpart in Wikidata. To ensure consistency and interpretability in the resulting KG, we ground generation of KG with the authored ontology based on extracted relations. Evaluation on benchmark datasets demonstrates competitive performance in knowledge graph construction task. Our work presents a promising direction for scalable KG construction pipeline with minimal human intervention, that yields high quality and human-interpretable KGs, which are interoperable with Wikidata semantics for potential knowledge base expansion.
title Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schema
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2412.20942