Misc3064: Unterschied zwischen den Versionen

Version vom 17. November 2022, 11:08 Uhr

Is Aligning Embedding Spaces a Challenging Task? An Analysis of the Existing Methods

Veröffentlichung: 2020 Februar
Art der Veröffentlichung: arxiv article
BibTeX

Kurzfassung
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 informa- tion, different KGs pose the problem of structural differences making the alignment of the KG embeddings more challenging. This paper pro- vides a theoretical analysis and comparison of the state-of-the-art align- ment 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 pretext of different applications.

DOI Link: abs/2002.09247 CoRR abs/2002.09247

Forschungsgruppe

Information Service Engineering

Forschungsgebiet

@@ Zeile 18: / Zeile 18: @@
 }}
 {{Publikation Details
+|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 informa- tion, different KGs pose the problem of structural differences making the alignment of the KG embeddings more challenging. This paper pro- vides a theoretical analysis and comparison of the state-of-the-art align- ment 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 pretext of different applications.
 |DOI Name=CoRR abs/2002.09247
 |Forschungsgruppe=Information Service Engineering
 }}