More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches

Kemas Wiharja; Jeff Z. Pan; Martin Kollingbaum; Yu Deng

doi:10.1007/978-3-030-04284-4_2

More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches

Kemas Wiharja, Jeff Z. Pan, Martin Kollingbaum, Yu Deng

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Constructing and maintaining large-scale good quality knowledge graphs present many challenges. Knowledge graph completion has been regarded a promising direction in the knowledge graph community. The majority of current work for knowledge graph completion approaches do not take the schema of a target knowledge graph as input. As a result, the triples generated by these approaches are not necessarily consistent with the schema of the target knowledge graph. This paper proposes to improve the correctness of knowledge graph completion based on Schema Aware Triple Classification (SATC), which enables sequential combinations of knowledge graph embedding approaches. Extensive experiments show that our proposed approaches can significantly improve the correctness of the new triples produced by knowledge graph embedding methods.

Original language	English
Title of host publication	Semantic Technology
Subtitle of host publication	8th Joint International Conference, JIST 2018, Awaji, Japan, November 26–28, 2018, Proceedings
Editors	Ryutaro Ichise, Freddy Lecue, Takahiro Kawamura, Dongyan Zhao, Stephen Muggleton, Kouji Kozaki
Place of Publication	Cham
Publisher	Springer
Pages	19-35
Number of pages	17
ISBN (Electronic)	978-3-030-04284-4
ISBN (Print)	978-3-030-04283-7
DOIs	https://doi.org/10.1007/978-3-030-04284-4_2
Publication status	Published - 14 Nov 2018
Event	The 8th Joint International Semantic Technology Conference - Awaji City, Japan Duration: 26 Nov 2018 → 28 Nov 2018 http://jist2018.knowledge-graph.jp/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer, Cham
Volume	11341
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	The 8th Joint International Semantic Technology Conference
Abbreviated title	JIST 2018
Country/Territory	Japan
City	Awaji City
Period	26/11/18 → 28/11/18
Internet address	http://jist2018.knowledge-graph.jp/

Keywords / Materials (for Non-textual outputs)

Knowledge graph
Embedding
Schema aware triple classification
Knowledge representation and reasoning
Approximate reasoning
Artificial Intelligence

Access to Document

10.1007/978-3-030-04284-4_2Licence: All Rights Reserved

https://link.springer.com/chapter/10.1007/978-3-030-04284-4_2Licence: All Rights Reserved

Cite this

Wiharja, K., Pan, J. Z., Kollingbaum, M., & Deng, Y. (2018). More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches. In R. Ichise, F. Lecue, T. Kawamura, D. Zhao, S. Muggleton, & K. Kozaki (Eds.), Semantic Technology: 8th Joint International Conference, JIST 2018, Awaji, Japan, November 26–28, 2018, Proceedings (pp. 19-35). (Lecture Notes in Computer Science; Vol. 11341). Springer. https://doi.org/10.1007/978-3-030-04284-4_2

Wiharja, Kemas ; Pan, Jeff Z. ; Kollingbaum, Martin et al. / More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches. Semantic Technology: 8th Joint International Conference, JIST 2018, Awaji, Japan, November 26–28, 2018, Proceedings. editor / Ryutaro Ichise ; Freddy Lecue ; Takahiro Kawamura ; Dongyan Zhao ; Stephen Muggleton ; Kouji Kozaki. Cham : Springer, 2018. pp. 19-35 (Lecture Notes in Computer Science).

@inproceedings{23361f40381f4bcaa15a9363f2d82943,

title = "More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches",

abstract = "Constructing and maintaining large-scale good quality knowledge graphs present many challenges. Knowledge graph completion has been regarded a promising direction in the knowledge graph community. The majority of current work for knowledge graph completion approaches do not take the schema of a target knowledge graph as input. As a result, the triples generated by these approaches are not necessarily consistent with the schema of the target knowledge graph. This paper proposes to improve the correctness of knowledge graph completion based on Schema Aware Triple Classification (SATC), which enables sequential combinations of knowledge graph embedding approaches. Extensive experiments show that our proposed approaches can significantly improve the correctness of the new triples produced by knowledge graph embedding methods.",

keywords = "Knowledge graph, Embedding, Schema aware triple classification, Knowledge representation and reasoning, Approximate reasoning, Artificial Intelligence",

author = "Kemas Wiharja and Pan, {Jeff Z.} and Martin Kollingbaum and Yu Deng",

year = "2018",

month = nov,

day = "14",

doi = "10.1007/978-3-030-04284-4_2",

language = "English",

isbn = "978-3-030-04283-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "19--35",

editor = "Ryutaro Ichise and Freddy Lecue and Takahiro Kawamura and Dongyan Zhao and Stephen Muggleton and Kouji Kozaki",

booktitle = "Semantic Technology",

address = "United Kingdom",

note = "The 8th Joint International Semantic Technology Conference, JIST 2018 ; Conference date: 26-11-2018 Through 28-11-2018",

url = "http://jist2018.knowledge-graph.jp/",

}

Wiharja, K, Pan, JZ, Kollingbaum, M & Deng, Y 2018, More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches. in R Ichise, F Lecue, T Kawamura, D Zhao, S Muggleton & K Kozaki (eds), Semantic Technology: 8th Joint International Conference, JIST 2018, Awaji, Japan, November 26–28, 2018, Proceedings. Lecture Notes in Computer Science, vol. 11341, Springer, Cham, pp. 19-35, The 8th Joint International Semantic Technology Conference, Awaji City, Japan, 26/11/18. https://doi.org/10.1007/978-3-030-04284-4_2

More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches. / Wiharja, Kemas; Pan, Jeff Z.; Kollingbaum, Martin et al.
Semantic Technology: 8th Joint International Conference, JIST 2018, Awaji, Japan, November 26–28, 2018, Proceedings. ed. / Ryutaro Ichise; Freddy Lecue; Takahiro Kawamura; Dongyan Zhao; Stephen Muggleton; Kouji Kozaki. Cham: Springer, 2018. p. 19-35 (Lecture Notes in Computer Science; Vol. 11341).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches

AU - Wiharja, Kemas

AU - Pan, Jeff Z.

AU - Kollingbaum, Martin

AU - Deng, Yu

PY - 2018/11/14

Y1 - 2018/11/14

N2 - Constructing and maintaining large-scale good quality knowledge graphs present many challenges. Knowledge graph completion has been regarded a promising direction in the knowledge graph community. The majority of current work for knowledge graph completion approaches do not take the schema of a target knowledge graph as input. As a result, the triples generated by these approaches are not necessarily consistent with the schema of the target knowledge graph. This paper proposes to improve the correctness of knowledge graph completion based on Schema Aware Triple Classification (SATC), which enables sequential combinations of knowledge graph embedding approaches. Extensive experiments show that our proposed approaches can significantly improve the correctness of the new triples produced by knowledge graph embedding methods.

AB - Constructing and maintaining large-scale good quality knowledge graphs present many challenges. Knowledge graph completion has been regarded a promising direction in the knowledge graph community. The majority of current work for knowledge graph completion approaches do not take the schema of a target knowledge graph as input. As a result, the triples generated by these approaches are not necessarily consistent with the schema of the target knowledge graph. This paper proposes to improve the correctness of knowledge graph completion based on Schema Aware Triple Classification (SATC), which enables sequential combinations of knowledge graph embedding approaches. Extensive experiments show that our proposed approaches can significantly improve the correctness of the new triples produced by knowledge graph embedding methods.

KW - Knowledge graph

KW - Embedding

KW - Schema aware triple classification

KW - Knowledge representation and reasoning

KW - Approximate reasoning

KW - Artificial Intelligence

U2 - 10.1007/978-3-030-04284-4_2

DO - 10.1007/978-3-030-04284-4_2

M3 - Conference contribution

SN - 978-3-030-04283-7

T3 - Lecture Notes in Computer Science

SP - 19

EP - 35

BT - Semantic Technology

A2 - Ichise, Ryutaro

A2 - Lecue, Freddy

A2 - Kawamura, Takahiro

A2 - Zhao, Dongyan

A2 - Muggleton, Stephen

A2 - Kozaki, Kouji

PB - Springer

CY - Cham

T2 - The 8th Joint International Semantic Technology Conference

Y2 - 26 November 2018 through 28 November 2018

ER -

Wiharja K, Pan JZ, Kollingbaum M, Deng Y. More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches. In Ichise R, Lecue F, Kawamura T, Zhao D, Muggleton S, Kozaki K, editors, Semantic Technology: 8th Joint International Conference, JIST 2018, Awaji, Japan, November 26–28, 2018, Proceedings. Cham: Springer. 2018. p. 19-35. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-04284-4_2

More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches

Abstract

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this