SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

TL;DR

This paper introduces SSP, a semantic space projection method for knowledge graph embedding that incorporates text descriptions to produce more interpretable and semantically meaningful representations, improving performance on key tasks.

Contribution

It proposes a novel semantic representation approach for knowledge graphs using a hierarchical generative process that captures multiple aspects and categories, enhancing interpretability.

Findings

Outperforms state-of-the-art baselines significantly

Provides more interpretable and semantically rich embeddings

Improves performance on question answering and entity classification

Abstract

Knowledge representation is an important, long-history topic in AI, and there have been a large amount of work for knowledge graph embedding which projects symbolic entities and relations into low-dimensional, real-valued vector space. However, most embedding methods merely concentrate on data fitting and ignore the explicit semantic expression, leading to uninterpretable representations. Thus, traditional embedding methods have limited potentials for many applications such as question answering, and entity classification. To this end, this paper proposes a semantic representation method for knowledge graph \textbf{(KSR)}, which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple. Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple. Extensive experiments justify our model outperforms other state-of-the-art baselines substantially.