# On2Vec: Embedding-based Relation Prediction for Ontology Population

arXiv: https://arxiv.org/abs/1809.02382 · HTML: https://mlsanity.com/paper/1809.02382/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2018.

## Built on by (most cited first, 6 of 6)

- [OntoZSL: Ontology-enhanced Zero-shot Learning](https://mlsanity.com/paper/2102.07339/) (2021)
- [Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts](https://mlsanity.com/paper/2103.08115/) (2021)
- [Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases](https://mlsanity.com/paper/2103.04283/) (2021)
- [Document Structure aware Relational Graph Convolutional Networks for Ontology Population](https://mlsanity.com/paper/2104.12950/) (2021)
- [Link Analysis meets Ontologies: Are Embeddings the Answer?](https://mlsanity.com/paper/2111.11710/) (2021)
- [Transforming Geospatial Ontologies by Homomorphisms](https://mlsanity.com/paper/2305.13135/) (2023)

## Abstract (arXiv)

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.