A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network

TL;DR

This paper introduces ConvKB, a convolutional neural network-based embedding model that improves knowledge base completion by capturing global relationships, achieving superior link prediction performance on benchmark datasets.

Contribution

ConvKB is the first to apply convolutional neural networks to knowledge base embedding for improved global relationship modeling.

Findings

Outperforms previous models on WN18RR and FB15k-237 datasets.

Effectively captures global relationships and transitional features.

Achieves state-of-the-art link prediction accuracy.

Abstract

In this paper, we propose a novel embedding model, named ConvKB, for knowledge base completion. Our model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases. In ConvKB, each triple (head entity, relation, tail entity) is represented as a 3-column matrix where each column vector represents a triple element. This 3-column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps. These feature maps are then concatenated into a single feature vector representing the input triple. The feature vector is multiplied with a weight vector via a dot product to return a score. This score is then used to predict whether the triple is valid or not. Experiments show that ConvKB achieves better link prediction performance than previous state-of-the-art embedding models on two benchmark datasets WN18RR and FB15k-237.