Paper Info
Title
A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization.
Abstract
In this paper, we introduce an embedding model, named CapsE, exploring a capsule network to model relationship triples textit{(subject, relation, object)}. Our CapsE represents each triple as a 3-column matrix where each column vector represents the embedding of an element in the triple. This 3-column matrix is then fed to a convolution layer where multiple filters are operated to generate different feature maps. These feature maps are used to construct capsules in the first capsule layer. Capsule layers are connected via dynamic routing mechanism. The last capsule layer consists of only one capsule to produce a vector output. The length of this vector output is used to measure the plausibility of the triple. Our proposed CapsE obtains state-of-the-art link prediction results for knowledge graph completion on two benchmark datasets: WN18RR and FB15k-237, and outperforms strong search personalization baselines on SEARCH17 dataset.
Year
DOI
Venue
2018
10.18653/v1/n19-1226
north american chapter of the association for computational linguistics
Field
DocType
Volume
Monad (category theory),Knowledge graph,Embedding,Matrix (mathematics),Convolution,Computer science,Algorithm,Artificial intelligence,Machine learning,Personalization,Column vector
Journal
abs/1808.04122
Citations 
PageRank 
References 
3
0.37
15
Authors
5
Name
Order
Citations
PageRank
Dai Quoc Nguyen110713.49
Thanh Vu2406.87
Tu Dinh Nguyen313420.58
Dat Quoc Nguyen424625.87
Dinh Q. Phung51469144.58