Top-k diversification for path queries in knowledge graphs

Christian Aebeloe; Vinay Setty; Gabriela Montoya; Katja Hose

Top-k diversification for path queries in knowledge graphs

Christian Aebeloe, Vinay Setty, Gabriela Montoya, Katja Hose

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

69 Downloads (Pure)

Abstract

To explore the relationships between entities in RDF graphs, property path queries were introduced in SPARQL 1.1. However, existing RDF engines return only reachability of the entities ignoring the intermediate nodes in the path. If the paths are output, they are too many, which makes it difficult for users to find the most relevant paths. To address this issue, we propose a generalized top-k ranking technique that balances the trade-off between relevance and diversity. We propose a shortest path based relevance scoring in combination with several path similarity measures for diversification. With preliminary experiments and examples, we show that our diversification strategies provide more novel paths as our technique prioritizes diversity over path length.

Original language	English
Title of host publication	Proceedings of the ISWC 2018 Posters & Demonstrations, Industry and Blue Sky Ideas Tracks
Editors	Marieke Van Erp, Madha Atre, Vanessa Lopez, Kavitha Srinivas, Carolona Fortuna
Number of pages	4
Publisher	CEUR Workshop Proceedings
Publication date	1 Jan 2018
Publication status	Published - 1 Jan 2018
Event	2018 ISWC Posters and Demonstrations, Industry and Blue Sky Ideas Tracks, ISWC-P and D-Industry-BlueSky 2018 - Monterey, United States Duration: 8 Oct 2018 → 12 Oct 2018

Conference

Conference	2018 ISWC Posters and Demonstrations, Industry and Blue Sky Ideas Tracks, ISWC-P and D-Industry-BlueSky 2018
Country/Territory	United States
City	Monterey
Period	08/10/2018 → 12/10/2018

Series	CEUR Workshop Proceedings
Volume	2180
ISSN	1613-0073

Access to Document

Final published versionFinal published version, 229 KB

http://ceur-ws.org/Vol-2180/paper-01.pdf

Cite this

Aebeloe, C., Setty, V., Montoya, G., & Hose, K. (2018). Top-k diversification for path queries in knowledge graphs. In M. Van Erp, M. Atre, V. Lopez, K. Srinivas, & C. Fortuna (Eds.), Proceedings of the ISWC 2018 Posters & Demonstrations, Industry and Blue Sky Ideas Tracks CEUR Workshop Proceedings. CEUR Workshop Proceedings Vol. 2180 http://ceur-ws.org/Vol-2180/paper-01.pdf

Aebeloe, Christian ; Setty, Vinay ; Montoya, Gabriela et al. / Top-k diversification for path queries in knowledge graphs. Proceedings of the ISWC 2018 Posters & Demonstrations, Industry and Blue Sky Ideas Tracks. editor / Marieke Van Erp ; Madha Atre ; Vanessa Lopez ; Kavitha Srinivas ; Carolona Fortuna. CEUR Workshop Proceedings, 2018. (CEUR Workshop Proceedings, Vol. 2180).

@inproceedings{73411b915dca44448e0a7d9d472fac66,

title = "Top-k diversification for path queries in knowledge graphs",

abstract = "To explore the relationships between entities in RDF graphs, property path queries were introduced in SPARQL 1.1. However, existing RDF engines return only reachability of the entities ignoring the intermediate nodes in the path. If the paths are output, they are too many, which makes it difficult for users to find the most relevant paths. To address this issue, we propose a generalized top-k ranking technique that balances the trade-off between relevance and diversity. We propose a shortest path based relevance scoring in combination with several path similarity measures for diversification. With preliminary experiments and examples, we show that our diversification strategies provide more novel paths as our technique prioritizes diversity over path length.",

author = "Christian Aebeloe and Vinay Setty and Gabriela Montoya and Katja Hose",

year = "2018",

month = jan,

day = "1",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR Workshop Proceedings",

editor = "{Van Erp}, Marieke and Madha Atre and Lopez, {Vanessa } and Kavitha Srinivas and Carolona Fortuna",

booktitle = "Proceedings of the ISWC 2018 Posters & Demonstrations, Industry and Blue Sky Ideas Tracks",

note = "2018 ISWC Posters and Demonstrations, Industry and Blue Sky Ideas Tracks, ISWC-P and D-Industry-BlueSky 2018 ; Conference date: 08-10-2018 Through 12-10-2018",

}

Aebeloe, C, Setty, V, Montoya, G & Hose, K 2018, Top-k diversification for path queries in knowledge graphs. in M Van Erp, M Atre, V Lopez, K Srinivas & C Fortuna (eds), Proceedings of the ISWC 2018 Posters & Demonstrations, Industry and Blue Sky Ideas Tracks. CEUR Workshop Proceedings, CEUR Workshop Proceedings, vol. 2180, 2018 ISWC Posters and Demonstrations, Industry and Blue Sky Ideas Tracks, ISWC-P and D-Industry-BlueSky 2018, Monterey, United States, 08/10/2018. <http://ceur-ws.org/Vol-2180/paper-01.pdf>

Top-k diversification for path queries in knowledge graphs. / Aebeloe, Christian; Setty, Vinay; Montoya, Gabriela et al.

Proceedings of the ISWC 2018 Posters & Demonstrations, Industry and Blue Sky Ideas Tracks. ed. / Marieke Van Erp; Madha Atre; Vanessa Lopez; Kavitha Srinivas; Carolona Fortuna. CEUR Workshop Proceedings, 2018. (CEUR Workshop Proceedings, Vol. 2180).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Top-k diversification for path queries in knowledge graphs

AU - Aebeloe, Christian

AU - Setty, Vinay

AU - Montoya, Gabriela

AU - Hose, Katja

PY - 2018/1/1

Y1 - 2018/1/1

N2 - To explore the relationships between entities in RDF graphs, property path queries were introduced in SPARQL 1.1. However, existing RDF engines return only reachability of the entities ignoring the intermediate nodes in the path. If the paths are output, they are too many, which makes it difficult for users to find the most relevant paths. To address this issue, we propose a generalized top-k ranking technique that balances the trade-off between relevance and diversity. We propose a shortest path based relevance scoring in combination with several path similarity measures for diversification. With preliminary experiments and examples, we show that our diversification strategies provide more novel paths as our technique prioritizes diversity over path length.

AB - To explore the relationships between entities in RDF graphs, property path queries were introduced in SPARQL 1.1. However, existing RDF engines return only reachability of the entities ignoring the intermediate nodes in the path. If the paths are output, they are too many, which makes it difficult for users to find the most relevant paths. To address this issue, we propose a generalized top-k ranking technique that balances the trade-off between relevance and diversity. We propose a shortest path based relevance scoring in combination with several path similarity measures for diversification. With preliminary experiments and examples, we show that our diversification strategies provide more novel paths as our technique prioritizes diversity over path length.

UR - http://www.scopus.com/inward/record.url?scp=85055345102&partnerID=8YFLogxK

M3 - Article in proceeding

AN - SCOPUS:85055345102

T3 - CEUR Workshop Proceedings

BT - Proceedings of the ISWC 2018 Posters & Demonstrations, Industry and Blue Sky Ideas Tracks

A2 - Van Erp, Marieke

A2 - Atre, Madha

A2 - Lopez, Vanessa

A2 - Srinivas, Kavitha

A2 - Fortuna, Carolona

PB - CEUR Workshop Proceedings

T2 - 2018 ISWC Posters and Demonstrations, Industry and Blue Sky Ideas Tracks, ISWC-P and D-Industry-BlueSky 2018

Y2 - 8 October 2018 through 12 October 2018

ER -

Top-k diversification for path queries in knowledge graphs

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Unleashing the Potential of Open Data

QWeb: Querying the Web of Data Easily and Efficiently

Cite this

Top-k diversification for path queries in knowledge graphs

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Projects

Unleashing the Potential of Open Data

QWeb: Querying the Web of Data Easily and Efficiently

Cite this