Abstract | ||
---|---|---|
Low-dimensional embeddings for knowledge graph entities and relations help preserve their latent semantics while enabling computation efficiency. These embeddings are often used to perform tasks such as knowledge graph completion, question answering and inference. Knowledge graph embedding methods aid in the representation of entities and relationships of a knowledge graph in continuous vector spaces. However, most existing techniques ignore the inherent hierarchical structure of entities present in the knowledge graph, defined by ontological relationships between entity types. This paper introduces a novel score function called GrCluster that helps fill that gap. GrCluster is a simple, intuitive and efficient scoring function that incorporates the entity hierarchical correlation into existing knowledge graph embeddings. The effectiveness of GrCluster is demonstrated by integrating it into several well known embedding models. The experimental results show consistent improvements across metrics and embedding models for the tasks of entity prediction and triplet classification.
|
Year | DOI | Venue |
---|---|---|
2020 | 10.1145/3341105.3373978 | SAC '20: The 35th ACM/SIGAPP Symposium on Applied Computing
Brno
Czech Republic
March, 2020 |
Keywords | DocType | ISBN |
knowledge representation, knowledge graph embeddings, representation learning, relational learning, hierarchy, wordnet | Conference | 978-1-4503-6866-7 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Varun Ranganathan | 1 | 0 | 0.34 |
Siddharth Suresh | 2 | 0 | 0.34 |
Yash Mathur | 3 | 0 | 0.34 |
S. Natarajan | 4 | 20 | 7.12 |
Denilson Barbosa | 5 | 610 | 43.52 |