Faithful Embeddings for EL++ Knowledge Bases
The Semantic Web – ISWC 2022: 21st International Semantic Web Conference, Virtual Event, October 23–27, 2022, Proceedings(2022)
摘要
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 E L + + . 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 E L + + embedding approaches.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要