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

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.
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)
Pages327–333
Number of pages7
ISBN (Electronic)9781948087292
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventNorth American Association for Computational Linguistics 2018: Human Language Technologies - Hyatt Regency, New Orleans, United States of America
Duration: 1 Jun 20186 Jun 2018
Conference number: 16th
http://naacl2018.org/

Conference

ConferenceNorth American Association for Computational Linguistics 2018
Abbreviated titleNAACL HLT 2018
CountryUnited States of America
CityNew Orleans
Period1/06/186/06/18
Internet address

Cite this

Quoc Nguyen, D., Nguyen, T. D., Nguyen, D. Q., & Phung, D. (2018). A novel embedding model for knowledge base completion based on convolutional neural network. In H. Ji, & A. Stent (Eds.), The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference Volume 2 (Short Papers) (pp. 327–333). Stroudsburg PA USA: Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/N18-2053
Quoc Nguyen, Dai ; Nguyen, Tu Dinh ; Nguyen, Dat Quoc ; Phung, Dinh. / A novel embedding model for knowledge base completion based on convolutional neural network. The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference Volume 2 (Short Papers). editor / Heng Ji ; Amanda Stent. Stroudsburg PA USA : Association for Computational Linguistics (ACL), 2018. pp. 327–333
@inproceedings{5a363baa440a45048545f0a4c27c700e,
title = "A novel embedding model for knowledge base completion based on convolutional neural network",
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.",
author = "{Quoc Nguyen}, Dai and Nguyen, {Tu Dinh} and Nguyen, {Dat Quoc} and Dinh Phung",
year = "2018",
doi = "10.18653/v1/N18-2053",
language = "English",
pages = "327–333",
editor = "Ji, {Heng } and Amanda Stent",
booktitle = "The 2018 Conference of the North American Chapter of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",

}

Quoc Nguyen, D, Nguyen, TD, Nguyen, DQ & Phung, D 2018, A novel embedding model for knowledge base completion based on convolutional neural network. in H Ji & A Stent (eds), The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference Volume 2 (Short Papers). Association for Computational Linguistics (ACL), Stroudsburg PA USA, pp. 327–333, North American Association for Computational Linguistics 2018, New Orleans, United States of America, 1/06/18. https://doi.org/10.18653/v1/N18-2053

A novel embedding model for knowledge base completion based on convolutional neural network. / Quoc Nguyen, Dai; Nguyen, Tu Dinh; Nguyen, Dat Quoc; Phung, Dinh.

The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference Volume 2 (Short Papers). ed. / Heng Ji; Amanda Stent. Stroudsburg PA USA : Association for Computational Linguistics (ACL), 2018. p. 327–333.

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

TY - GEN

T1 - A novel embedding model for knowledge base completion based on convolutional neural network

AU - Quoc Nguyen, Dai

AU - Nguyen, Tu Dinh

AU - Nguyen, Dat Quoc

AU - Phung, Dinh

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

U2 - 10.18653/v1/N18-2053

DO - 10.18653/v1/N18-2053

M3 - Conference Paper

SP - 327

EP - 333

BT - The 2018 Conference of the North American Chapter of the Association for Computational Linguistics

A2 - Ji, Heng

A2 - Stent, Amanda

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg PA USA

ER -

Quoc Nguyen D, Nguyen TD, Nguyen DQ, Phung D. A novel embedding model for knowledge base completion based on convolutional neural network. In Ji H, Stent A, editors, The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference Volume 2 (Short Papers). Stroudsburg PA USA: Association for Computational Linguistics (ACL). 2018. p. 327–333 https://doi.org/10.18653/v1/N18-2053