Discovering Fine-Grained Semantics in Knowledge Graph Relations

TL;DR

This paper proposes a method to automatically discover and interpret fine-grained semantics of relations in knowledge graphs by clustering entity and relation embeddings, improving understanding of multi-relational data.

Contribution

It introduces a novel strategy for identifying multiple sub-relations of polysemous relations using entity types and embedding clustering, with automatic determination of sub-relation count.

Findings

Successfully discovers meaningful sub-relations in knowledge graphs.

Automatically determines the optimal number of sub-relations.

Enhances relation interpretability for various knowledge graph applications.

Abstract

When it comes to comprehending and analyzing multi-relational data, the semantics of relations are crucial. Polysemous relations between different types of entities, that represent multiple semantics, are common in real-world relational datasets represented by knowledge graphs. For numerous use cases, such as entity type classification, question answering and knowledge graph completion, the correct semantic interpretation of these relations is necessary. In this work, we provide a strategy for discovering the different semantics associated with abstract relations and deriving many sub-relations with fine-grained meaning. To do this, we leverage the types of the entities associated with the relations and cluster the vector representations of entities and relations. The suggested method is able to automatically discover the best number of sub-relations for a polysemous relation and determine their semantic interpretation, according to our empirical evaluation.