Enrichment Ontology via Linked Data

Enrichment Ontology via Linked Data

Salvia Praga (Poland University of Worcester, Poland)
Copyright: © 2019 |Pages: 13
DOI: 10.4018/978-1-5225-7338-8.ch005

Abstract

The automatic construction of ontologies from texts is usually based on the text itself, and the domain described is limited to the content of the text. In order to design semantically richer ontologies, the authors propose to extend the classical methods of ontology construction (1) by taking into account the text from the point of view of its structure and its content to build a first nucleus ontology and (2) enriching the ontology obtained by exploiting external resources (general texts and controlled vocabularies of the same domain). This chapter describes how these different resources are analyzed and exploited using linked data properties.
Chapter Preview
Top

Introduction

In the last years, the Linked Data paradigm has found a huge application when combined with the publication of data with liberal licenses. The Open Data Movement, which aims to release huge data sets often from local government authorities, embraced the Linked Data technologies and best practices to publish a plethora of different interlinked data sets.

Roughly speaking, a bunch of data published with an open license is intended to be freely available to everyone to use and republished without restriction from copyright, patents or other restrictions. Where Open Data meets Linked Data, we have Linked Open Data1. The Linked Open Data movement has experienced exponential growth in term of published data sets. Within four years, the number of published data sets has grown from 12 to 295 (Jentzsch, 2011). With all this development of linked data and semantic web, ontologies still later, we've come out with this idea “using these data to enrich an ontology “first, we must know the process of ontology enrichment which include ontology learning.

Ontology Learning

  • Ontology learning is the process of acquiring (constructing or integrating) an ontology.

  • (Semi-) automatically. The acquisition of ontologies can be performed through three.

  • Major approaches: (Petasis, Karkaletsis, Paliouras, Krithara, & Zavitsanos, 2011).

  • By integrating existing ontologies. The integration process tries to capture commonalities among ontologies that convey the same or similar domains, in order to derive a new ontology.

  • By constructing an ontology from scratch or by extending (enriching) an existing.

  • Ontology, usually based on information extracted from domain-specific content.

  • By specializing a generic ontology, in order to adapt it to a specific domain. Ontology learning is not simply a replication of existing work under a different name.

  • It adds novel aspects to the problem of knowledge acquisition:

  • Ontology learning combines research from knowledge representation, logic, philosophy, databases, machine learning, natural language processing, image/audio/video analysis, etc.

  • Ontology learning in the context of the Semantic Web must deal with the massive and heterogeneous data of the World Wide Web and thus improve existing approaches for knowledge acquisition, which target mostly small and homogeneous data collections. (Petasis, Karkaletsis, Paliouras, Krithara, & Zavitsanos, 2011)

  • Substantial effort is being put into the development of extensive and rigorous evaluation methods in order to evaluate ontology learning approaches on welldefined tasks with well-defined evaluation criteria.

Ontology Enrichment

Ontology enrichment is the process of extending an ontology, through the addition of new concepts, relations and rules. It is performed every time that the existing domain knowledge is not sufficient to explain the information extracted from the corpus or linked data in our case.

Top

The purpose of this section is to discuss state-of-the-art

Complete Chapter List

Search this Book:
Reset