A novel embedding model for knowledge base completion based on convolutional neural network

Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

503 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationThe 2018 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, Proceedings of the Conference Volume 2 (Short Papers)
EditorsHeng Ji, Amanda Stent
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Number of pages7
ISBN (Electronic)9781948087292
Publication statusPublished - 2018
Externally publishedYes
EventNorth American Association for Computational Linguistics 2018 - Hyatt Regency, New Orleans, United States of America
Duration: 1 Jun 20186 Jun 2018
Conference number: 16th
https://www.aclweb.org/anthology/volumes/N18-1/ (Proceedings )


ConferenceNorth American Association for Computational Linguistics 2018
Abbreviated titleNAACL HLT 2018
Country/TerritoryUnited States of America
CityNew Orleans
Internet address

Cite this