Is Aligning Embedding Spaces a Challenging Task? A Study on Heterogeneous Embedding Alignment Methods
This work provides a theoretical assessment for researchers and practitioners in knowledge-driven applications like question answering, but it is incremental as it reviews existing methods without introducing new techniques.
The paper analyzes and compares state-of-the-art methods for aligning heterogeneous embedding spaces, such as those from knowledge graphs and words, to address challenges like structural differences and multilinguality, but does not report specific numerical results or improvements.
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.