Interpreting Knowledge Graph Relation Representation from Word Embeddings
This work provides theoretical insights for researchers in knowledge representation, but it is incremental as it builds on existing understanding without introducing new methods.
The paper tackled the problem of interpreting how knowledge graph embedding models capture semantic information by categorizing relations into three types and deriving explicit representation requirements, showing that empirical properties and performance differences of leading methods align with their analysis.
Many models learn representations of knowledge graph data by exploiting its low-rank latent structure, encoding known relations between entities and enabling unknown facts to be inferred. To predict whether a relation holds between entities, embeddings are typically compared in the latent space following a relation-specific mapping. Whilst their predictive performance has steadily improved, how such models capture the underlying latent structure of semantic information remains unexplained. Building on recent theoretical understanding of word embeddings, we categorise knowledge graph relations into three types and for each derive explicit requirements of their representations. We show that empirical properties of relation representations and the relative performance of leading knowledge graph representation methods are justified by our analysis.