A Self-matching Training Method with Annotation Embedding Models for Ontology Subsumption Prediction

arXiv:2402.16278v1 Announce Type: cross
Abstract: Recently, ontology embeddings representing entities in a low-dimensional space have been proposed for ontology completion. However, the ontology embeddings for concept subsumption prediction do not address the difficulties of similar and isolated entities and fail to extract the global information of annotation axioms from an ontology. In this paper, we propose a self-matching training method for the two ontology embedding models: Inverted-index Matrix Embedding (InME) and Co-occurrence Matrix Embedding (CoME). The two embeddings capture the …

abstract annotation arxiv concept cs.ai cs.cl cs.lg embedding embedding models embeddings extract global information low ontology prediction space training type