REVIEW 2 cited by
Faithiful Embeddings for EL++ Knowledge Bases
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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 for protein-protein prediction show that BoxEL outperforms traditional knowledge graph embedding methods as well as state-of-the-art EL++ embedding approaches.
Forward citations
Cited by 2 Pith papers
-
NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning
NeurOWL is a neuro-symbolic pipeline that verifies subsumptions in incomplete OWL ontologies and explains them with suggested missing axioms.
-
Language Models as Ontology Encoders
OnT combines pretrained language models with hyperbolic embeddings and role rotations to encode EL ontologies, and reports better axiom prediction and inference than existing methods.
Discussion (0). Continue with ORCID to comment.