Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Integrating ontologies and vector space embeddings using conceptual spaces

Bouraoui, Zied, Gutierrez Basulto, Victor ORCID: and Schockaert, Steven ORCID: 2022. Integrating ontologies and vector space embeddings using conceptual spaces. Presented at: International Research School in Artificial Intelligence in Bergen (AIB 2022), 7-11 June 2022. The OpenAccess Series in Informatics. International Research School in Artificial Intelligence in Bergen. Open Access Series in Informatics (OASIcs) , vol.99 Dagstuhl, Germany: Dagstuhl Publishing, 3:1-3:30. 10.4230/OASIcs.AIB.2022.3

[thumbnail of OASIcs-AIB-2022-3.pdf]
PDF - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview


Ontologies and vector space embeddings are among the most popular frameworks for encoding conceptual knowledge. Ontologies excel at capturing the logical dependencies between concepts in a precise and clearly defined way. Vector space embeddings excel at modelling similarity and analogy. Given these complementary strengths, there is a clear need for frameworks that can combine the best of both worlds. In this paper, we present an overview of our recent work in this area. We first discuss the theory of conceptual spaces, which was proposed in the 1990s by Gärdenfors as an intermediate representation layer in between embeddings and symbolic knowledge bases. We particularly focus on a number of recent strategies for learning conceptual space representations from data. Next, building on the idea of conceptual spaces, we discuss approaches where relational knowledge is modelled in terms of geometric constraints. Such approaches aim at a tight integration of symbolic and geometric representations, which unfortunately comes with a number of limitations. For this reason, we finally also discuss methods in which similarity, and other forms of conceptual relatedness, are derived from vector space embeddings and subsequently used to support flexible forms of reasoning with ontologies, thus enabling a looser integration between embeddings and symbolic knowledge.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Dagstuhl Publishing
ISBN: 9783959772280
ISSN: 2190-6807
Date of First Compliant Deposit: 31 March 2022
Date of Acceptance: 6 March 2022
Last Modified: 18 Jan 2023 13:18

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics