Neighborhood mixture model for knowledge base completion

Dat Quoc Nguyen; Kairit Sirts; Lizhen Qu; Mark Johnson

doi:10.18653/v1/K16-1005

Neighborhood mixture model for knowledge base completion

Dat Quoc Nguyen, Kairit Sirts, Lizhen Qu, Mark Johnson

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

21 Citations (Scopus)

Abstract

Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete. In this paper, we define a novel entity representation as a mixture of its neighborhood in the knowledge base and apply this technique on TransE—a well-known embedding model for knowledge base completion. Experimental results show that the neighborhood information significantly helps to improve the results of the TransE, leading to better performance than obtained by other state-of-the-art embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.

Original language	English
Title of host publication	CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference
Editors	Yoav Goldberg, Stefan Riezler
Place of Publication	Stroudsburg PA USA
Publisher	Association for Computational Linguistics (ACL)
Pages	40-50
Number of pages	11
ISBN (Electronic)	9781945626197
DOIs	https://doi.org/10.18653/v1/K16-1005
Publication status	Published - 2016
Externally published	Yes
Event	Conference on Natural Language Learning 2016 - Berlin, Germany Duration: 11 Aug 2016 → 12 Aug 2016 Conference number: 20th https://www.conll.org/2016 https://www.aclweb.org/anthology/volumes/K16-1/ (Proceedings)

Conference

Conference	Conference on Natural Language Learning 2016
Abbreviated title	CoNLL 2016
Country	Germany
City	Berlin
Period	11/08/16 → 12/08/16
Internet address	https://www.conll.org/2016 https://www.aclweb.org/anthology/volumes/K16-1/ (Proceedings)

Keywords

Embedding model
Entity prediction
Knowledge base completion
Link prediction
Mixture model
Relation prediction
Triple classification

Access to Document

10.18653/v1/K16-1005

288982529-oaFinal published version, 185 KB

Link to publication in Scopus

Cite this

Nguyen, D. Q., Sirts, K., Qu, L., & Johnson, M. (2016). Neighborhood mixture model for knowledge base completion. In Y. Goldberg, & S. Riezler (Eds.), CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference (pp. 40-50). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/K16-1005

Nguyen, Dat Quoc ; Sirts, Kairit ; Qu, Lizhen ; Johnson, Mark. / Neighborhood mixture model for knowledge base completion. CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference. editor / Yoav Goldberg ; Stefan Riezler. Stroudsburg PA USA : Association for Computational Linguistics (ACL), 2016. pp. 40-50

@inproceedings{99308820533448dca015f00b0c32a2aa,

title = "Neighborhood mixture model for knowledge base completion",

abstract = "Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete. In this paper, we define a novel entity representation as a mixture of its neighborhood in the knowledge base and apply this technique on TransE—a well-known embedding model for knowledge base completion. Experimental results show that the neighborhood information significantly helps to improve the results of the TransE, leading to better performance than obtained by other state-of-the-art embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.",

keywords = "Embedding model, Entity prediction, Knowledge base completion, Link prediction, Mixture model, Relation prediction, Triple classification",

author = "Nguyen, {Dat Quoc} and Kairit Sirts and Lizhen Qu and Mark Johnson",

year = "2016",

doi = "10.18653/v1/K16-1005",

language = "English",

pages = "40--50",

editor = "Goldberg, {Yoav } and Stefan Riezler",

booktitle = "CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

note = "Conference on Natural Language Learning 2016, CoNLL 2016 ; Conference date: 11-08-2016 Through 12-08-2016",

url = "https://www.conll.org/2016, https://www.aclweb.org/anthology/volumes/K16-1/",

}

Nguyen, DQ, Sirts, K, Qu, L & Johnson, M 2016, Neighborhood mixture model for knowledge base completion. in Y Goldberg & S Riezler (eds), CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference. Association for Computational Linguistics (ACL), Stroudsburg PA USA, pp. 40-50, Conference on Natural Language Learning 2016, Berlin, Germany, 11/08/16. https://doi.org/10.18653/v1/K16-1005

Neighborhood mixture model for knowledge base completion. / Nguyen, Dat Quoc; Sirts, Kairit; Qu, Lizhen; Johnson, Mark.

CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference. ed. / Yoav Goldberg; Stefan Riezler. Stroudsburg PA USA : Association for Computational Linguistics (ACL), 2016. p. 40-50.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Neighborhood mixture model for knowledge base completion

AU - Nguyen, Dat Quoc

AU - Sirts, Kairit

AU - Qu, Lizhen

AU - Johnson, Mark

N1 - Conference code: 20th

PY - 2016

Y1 - 2016

N2 - Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete. In this paper, we define a novel entity representation as a mixture of its neighborhood in the knowledge base and apply this technique on TransE—a well-known embedding model for knowledge base completion. Experimental results show that the neighborhood information significantly helps to improve the results of the TransE, leading to better performance than obtained by other state-of-the-art embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.

AB - Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete. In this paper, we define a novel entity representation as a mixture of its neighborhood in the knowledge base and apply this technique on TransE—a well-known embedding model for knowledge base completion. Experimental results show that the neighborhood information significantly helps to improve the results of the TransE, leading to better performance than obtained by other state-of-the-art embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.

KW - Embedding model

KW - Entity prediction

KW - Knowledge base completion

KW - Link prediction

KW - Mixture model

KW - Relation prediction

KW - Triple classification

UR - http://www.scopus.com/inward/record.url?scp=85018692437&partnerID=8YFLogxK

U2 - 10.18653/v1/K16-1005

DO - 10.18653/v1/K16-1005

M3 - Conference Paper

SP - 40

EP - 50

BT - CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference

A2 - Goldberg, Yoav

A2 - Riezler, Stefan

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg PA USA

T2 - Conference on Natural Language Learning 2016

Y2 - 11 August 2016 through 12 August 2016

ER -

Nguyen DQ, Sirts K, Qu L, Johnson M. Neighborhood mixture model for knowledge base completion. In Goldberg Y, Riezler S, editors, CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference. Stroudsburg PA USA: Association for Computational Linguistics (ACL). 2016. p. 40-50 https://doi.org/10.18653/v1/K16-1005