Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods
A two-dimensional taxonomy is proposed: the first dimension categorises models based on their methodology, including translation-based models, tensor factorisation-based models, deep neural network-based models, logic rule-based models, and hyperedge expansion-based models, and hyperedge expansion-based models.
Xiao-Huan Lu, L. Tupikina, Mehwish Alam
· arXiv.org · 1 citation