Is Aligning Embedding Spaces a Challenging Task? A Study on Heterogeneous Embedding Alignment Methods

TL;DR

This paper provides a theoretical analysis and comparison of various methods for aligning heterogeneous embedding spaces, specifically in the context of knowledge graphs and word representations, highlighting their challenges and limitations.

Contribution

It offers a comprehensive theoretical evaluation of state-of-the-art alignment methods for heterogeneous embeddings, addressing structural differences and application-specific challenges.

Findings

Alignment methods vary in effectiveness depending on the application.

Structural differences in KGs pose significant challenges for embedding alignment.

Theoretical insights reveal limitations of current alignment techniques.

Abstract

Representation Learning of words and Knowledge Graphs (KG) into low dimensional vector spaces along with its applications to many real-world scenarios have recently gained momentum. In order to make use of multiple KG embeddings for knowledge-driven applications such as question answering, named entity disambiguation, knowledge graph completion, etc., alignment of different KG embedding spaces is necessary. In addition to multilinguality and domain-specific information, different KGs pose the problem of structural differences making the alignment of the KG embeddings more challenging. This paper provides a theoretical analysis and comparison of the state-of-the-art alignment methods between two embedding spaces representing entity-entity and entity-word. This paper also aims at assessing the capability and short-comings of the existing alignment methods on the pretext of different applications.