Survey on Embedding Models for Knowledge Graph and its Applications

Download

• Paper
• PDF

Abstract

Knowledge Graph (KG) is a graph-based data structure to represent facts of the world where nodes represent real-world entities or abstract concepts and edges represent relations between the entities. Graph as representation for knowledge has several drawbacks like data sparsity, computational complexity and manual feature engineering. Knowledge Graph embedding tackles these drawbacks by representing entities and relations in a low-dimensional vector space by capturing the semantic relations between them. There are different KG embedding models. Here, we discuss translation-based and neural network-based embedding models which differ based on semantic property, scoring function and architecture they use. Further, we discuss applications of KG in some domains that use deep learning models and leverage social media data.

Citation

Pote, M. (2024). Survey on Embedding Models for Knowledge Graph and its Applications. arXiv preprint arXiv:2404.09167.

@article{pote2024survey,
  title   = {Survey on Embedding Models for Knowledge Graph and its Applications},
  author  = {Pote, Manita},
  journal = {arXiv preprint arXiv:2404.09167},
  year    = {2024},
  url     = {https://arxiv.org/abs/2404.09167}
}