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

2020/02/21 by Biswas, Russa, Alam, Mehwish, Sack, Harald
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2002.09247

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.

Related

• A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs
• Knowledge Graph Embedding Methods for Entity Alignment: An Experimental Review
• Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning
• LLM-Align: Utilizing Large Language Models for Entity Alignment in Knowledge Graphs
• What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings