English

A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization

Computation and Language 2019-03-07 v3 Information Retrieval

Abstract

In this paper, we introduce an embedding model, named CapsE, exploring a capsule network to model relationship triples (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 reconstructed into corresponding capsules which are then routed to another capsule to produce a continuous vector. The length of this vector is used to measure the plausibility score of the triple. Our proposed CapsE obtains better performance than previous state-of-the-art embedding models for knowledge graph completion on two benchmark datasets WN18RR and FB15k-237, and outperforms strong search personalization baselines on SEARCH17.

Keywords

Cite

@article{arxiv.1808.04122,
  title  = {A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization},
  author = {Dai Quoc Nguyen and Thanh Vu and Tu Dinh Nguyen and Dat Quoc Nguyen and Dinh Phung},
  journal= {arXiv preprint arXiv:1808.04122},
  year   = {2019}
}

Comments

To appear in Proceedings of NAACL 2019. 10 pages

R2 v1 2026-06-23T03:31:48.245Z