Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

OWL2Vec4OA: Tailoring Knowledge Graph Embeddings for Ontology Alignment

Sevinj Teymurova, Ernesto Jiménez-Ruiz, Tillman Weyde, Jiaoyan Chen

TL;DR

The theoretical foundations, implementation details, and experimental evaluation of the proposed OWL2Vec4OA extension are presented, demonstrating its potential effectiveness for ontology alignment tasks.

Abstract

Ontology alignment is integral to achieving semantic interoperability as the number of available ontologies covering intersecting domains is increasing. This paper proposes OWL2Vec4OA, an extension of the ontology embedding system OWL2Vec*. While OWL2Vec* has emerged as a powerful technique for ontology embedding, it currently lacks a mechanism to tailor the embedding to the ontology alignment task. OWL2Vec4OA incorporates edge confidence values from seed mappings to guide the random walk strategy. We present the theoretical foundations, implementation details, and experimental evaluation of our proposed extension, demonstrating its potential effectiveness for ontology alignment tasks.

OWL2Vec4OA: Tailoring Knowledge Graph Embeddings for Ontology Alignment

TL;DR

The theoretical foundations, implementation details, and experimental evaluation of the proposed OWL2Vec4OA extension are presented, demonstrating its potential effectiveness for ontology alignment tasks.

Abstract

Ontology alignment is integral to achieving semantic interoperability as the number of available ontologies covering intersecting domains is increasing. This paper proposes OWL2Vec4OA, an extension of the ontology embedding system OWL2Vec*. While OWL2Vec* has emerged as a powerful technique for ontology embedding, it currently lacks a mechanism to tailor the embedding to the ontology alignment task. OWL2Vec4OA incorporates edge confidence values from seed mappings to guide the random walk strategy. We present the theoretical foundations, implementation details, and experimental evaluation of our proposed extension, demonstrating its potential effectiveness for ontology alignment tasks.
Paper Structure (20 sections, 1 equation, 4 figures, 2 tables, 1 algorithm)

This paper contains 20 sections, 1 equation, 4 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Ontologies and knowledge graphs.
  4. Ontology alignment
  5. LogMap
  6. Random walks
  7. OWL2Vec.
  8. Related Work
  9. Ontology embeddings with OWL2Vec4OA
  10. Ontology projection.
  11. Ontology alignment.
  12. Graph merger and Edge Weighting.
  13. Biased random walks.
  14. Document generator and Word2Vec embeddings.
  15. Evaluation
  16. ...and 5 more sections

Figures (4)

  • Figure 1: Fragment of an alignment between HeLiS and FoodOn (adapted from chen2021augmenting). The green dash arrow denotes mappings with confidence values ranging from [0,1]. Blue arrows represent the inverse of the predicate rdfs:subClassOf.
  • Figure 2: General architecture of LogMap.
  • Figure 3: General architecture of OWL2Vec*
  • Figure 4: General architecture of OWL2Vec4OA