DELE: Deductive EL++ Embeddings for Knowledge Base Completion

Tracking #: 796-1787

Flag : Review Assignment Stage

Authors: 

Olga Mashkova
Fernando Zhapa-Camacho
Robert Hoehndorf

Responsible editor: 

Guest Editors NeSy 2024

Submission Type: 

Article in Special Issue (note in cover letter)

Full PDF Version: 

Cover Letter: 

Dear Editors, Please find our manuscript entitled "DELE: Deductive EL++ Embeddings for Knowledge Base Completion" for your consideration. We submit this manuscript for the NeSy 2024 special issue as an extended version of the manuscript "Enhancing geometric ontology embeddings for EL++ with negative sampling and deductive closure filtering" published at the NeSy 2024 conference (paper # 51). In our previous work, we evaluated a set of embedding methods for EL++ ontologies based on high-dimensional ball representation, incorporating losses that take into consideration both the deductive closure and different types of negatives and propose a fast approximate algorithm for the deductive closure computation for EL++ theories. In the extended version, we consider a broader range of EL++ ontology embedding methods, propose loss functions for all types of negatives, include an extensive set of inference rules for computing the deductive closure and introduce novel evaluation methods accounting for the deductive closure. Please do not hesitate to contact us should you require any further information. Thank you for considering our work. Sincerely, The authors.

Tags: 

  • Under Review