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

Faithful embeddings for EL++ knowledge bases

Xiong, Bo, Potyka, Nico, Tran, Trung-Kien, Nayyeri, Mojtaba and Staab, Steffen 2022. Faithful embeddings for EL++ knowledge bases. Presented at: International Semantic Web Conference (ISWC 2022), Hangzhou, China, 23-27 October 2022. The Semantic Web – ISWC 2022. Lecture Notes in Computer Science , vol.13489 (13489) Springer Cham, pp. 22-38. 10.1007/978-3-031-19433-7_2

Full text not available from this repository.


Recently, increasing efforts are put into learning continual representations for symbolic knowledge bases (KBs). However, these approaches either only embed the data-level knowledge (ABox) or suffer from inherent limitations when dealing with concept-level knowledge (TBox), i.e., they cannot faithfully model the logical structure present in the KBs. We present BoxEL, a geometric KB embedding approach that allows for better capturing the logical structure (i.e., ABox and TBox axioms) in the description logic EL++. BoxEL models concepts in a KB as axis-parallel boxes that are suitable for modeling concept intersection, entities as points inside boxes, and relations between concepts/entities as affine transformations. We show theoretical guarantees (soundness) of BoxEL for preserving logical structure. Namely, the learned model of BoxEL embedding with loss 0 is a (logical) model of the KB. Experimental results on (plausible) subsumption reasonings and a real-world application–protein-protein prediction show that BoxEL outperforms traditional knowledge graph embedding methods as well as state-of-the-art EL++ embedding approaches.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Springer Cham
ISBN: 978-3-031-19432-0
Last Modified: 13 Jun 2023 13:31

Actions (repository staff only)

Edit Item Edit Item