# Interpreting Knowledge Graph Relation Representation from Word Embeddings

arXiv: https://arxiv.org/abs/1909.11611 · HTML: https://mlsanity.com/paper/1909.11611/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 1 of 1)

- [Modelling Multi-relations for Convolutional-based Knowledge Graph Embedding](https://mlsanity.com/paper/2210.11711/) (2022)

## Abstract (arXiv)

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.