A neural embedding model with relations as output weights is claimed to be fully expressive and to support rule injection without grounding for implication and equivalence rules.
Classification ability of single hidden layer feedforward neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical Rules
A neural embedding model with relations as output weights is claimed to be fully expressive and to support rule injection without grounding for implication and equivalence rules.