Extracting Domain-specific Concepts from Large-scale Linked Open Data

TL;DR

This paper introduces a methodology for extracting domain-specific concepts from large-scale linked open data, aiding the construction of specialized ontologies with minimal manual effort.

Contribution

It presents a novel approach that links LOD vocabulary with domain terms to automatically generate initial domain ontologies.

Findings

Successfully extracted a polymer materials ontology from Wikidata

Demonstrated the method's applicability to general class hierarchy datasets

Evaluated concept coverage using NLP and technical dictionaries

Abstract

We propose a methodology for extracting concepts for a target domain from large-scale linked open data (LOD) to support the construction of domain ontologies providing field-specific knowledge and definitions. The proposed method defines search entities by linking the LOD vocabulary with technical terms related to the target domain. The search entities are then used as a starting point for obtaining upper-level concepts in the LOD, and the occurrences of common upper-level entities and the chain-of-path relationships are examined to determine the range of conceptual connections in the target domain. A technical dictionary index and natural language processing are used to evaluate whether the extracted concepts cover the domain. As an example of extracting a class hierarchy from LOD, we used Wikidata to construct a domain ontology for polymer materials and physical properties. The proposed method can be applied to general datasets with class hierarchies, and it allows ontology developers to create an initial model of the domain ontology for their own purposes.