Joint Embeddings of Hierarchical Categories and Entities

TL;DR

This paper introduces a framework that embeds entities and hierarchical categories into a semantic space, effectively integrating structured knowledge and taxonomy hierarchies to improve semantic relatedness and concept categorization.

Contribution

It presents a novel embedding framework that incorporates category hierarchies and structured knowledge, handling both single-word and multi-word concepts with superior performance.

Findings

Improved semantic relatedness computation between entities and categories.

Enhanced concept categorization accuracy.

Effective handling of multi-word concepts.

Abstract

Due to the lack of structured knowledge applied in learning distributed representation of categories, existing work cannot incorporate category hierarchies into entity information.~We propose a framework that embeds entities and categories into a semantic space by integrating structured knowledge and taxonomy hierarchy from large knowledge bases. The framework allows to compute meaningful semantic relatedness between entities and categories.~Compared with the previous state of the art, our framework can handle both single-word concepts and multiple-word concepts with superior performance in concept categorization and semantic relatedness.