On2Vec: Embedding-based Relation Prediction for Ontology Population

TL;DR

On2Vec is a new translation-based embedding method designed to handle complex semantic relations in ontology graphs, improving relation prediction and verification for ontology population tasks.

Contribution

It introduces a novel embedding approach that captures comprehensive semantic relations and hierarchical structures in ontologies, addressing limitations of existing methods.

Findings

On2Vec outperforms existing methods in relation prediction accuracy.

The model effectively captures hierarchical and complex semantic relations.

Experiments show significant improvements in ontology population tasks.

Abstract

Populating ontology graphs represents a long-standing problem for the Semantic Web community. Recent advances in translation-based graph embedding methods for populating instance-level knowledge graphs lead to promising new approaching for the ontology population problem. However, unlike instance-level graphs, the majority of relation facts in ontology graphs come with comprehensive semantic relations, which often include the properties of transitivity and symmetry, as well as hierarchical relations. These comprehensive relations are often too complex for existing graph embedding methods, and direct application of such methods is not feasible. Hence, we propose On2Vec, a novel translation-based graph embedding method for ontology population. On2Vec integrates two model components that effectively characterize comprehensive relation facts in ontology graphs. The first is the Component-specific Model that encodes concepts and relations into low-dimensional embedding spaces without a loss of relational properties; the second is the Hierarchy Model that performs focused learning of hierarchical relation facts. Experiments on several well-known ontology graphs demonstrate the promising capabilities of On2Vec in predicting and verifying new relation facts. These promising results also make possible significant improvements in related methods.