Ontology matching evaluation: A statistical perspective

M. Mohammadi; Wout Hofman; Yao Hua Tan

Ontology matching evaluation: A statistical perspective

M. Mohammadi, Wout Hofman, Yao Hua Tan

Information and Communication Technology

Research output: Contribution to conference › Poster › Scientific

65 Downloads (Pure)

Abstract

This paper proposes statistical approaches to test if the difference between two ontology matchers is real. Specifically, the performances of the matchers over multiple data sets are obtained and based on their performances, the conclusion can be drawn whether one method is better than one another or not. To do so, the paired t-test and Wilcoxon signed rank test are proposed and the comparisons over six recently proposed methods are reported.

Original language	English
Pages	231-232
Number of pages	2
Publication status	Published - 2016
Event	The Eleventh International Workshop on Ontology Matching: collocated with the 15th International Semantic Web Conference - Kobe, Japan Duration: 18 Oct 2016 → … Conference number: 11 http://om2016.ontologymatching.org/#ap

Conference

Conference	The Eleventh International Workshop on Ontology Matching
Abbreviated title	OM-2016
Country/Territory	Japan
City	Kobe
Period	18/10/16 → …
Internet address	http://om2016.ontologymatching.org/#ap

Keywords

Evaluation
Ontology alignment
Paired t-test
Statistical inference
Wilcoxon signed rank test

Access to Document

om2016_poster3Final published version, 47.5 KB

Cite this

@conference{38fd65d2af3749f597a469f5c7dd01d1,

title = "Ontology matching evaluation: A statistical perspective",

abstract = "This paper proposes statistical approaches to test if the difference between two ontology matchers is real. Specifically, the performances of the matchers over multiple data sets are obtained and based on their performances, the conclusion can be drawn whether one method is better than one another or not. To do so, the paired t-test and Wilcoxon signed rank test are proposed and the comparisons over six recently proposed methods are reported.",

keywords = "Evaluation, Ontology alignment, Paired t-test, Statistical inference, Wilcoxon signed rank test",

author = "M. Mohammadi and Wout Hofman and Tan, {Yao Hua}",

year = "2016",

language = "English",

pages = "231--232",

note = "The Eleventh International Workshop on Ontology Matching : collocated with the 15th International Semantic Web Conference, OM-2016 ; Conference date: 18-10-2016",

url = "http://om2016.ontologymatching.org/#ap",

}

TY - CONF

T1 - Ontology matching evaluation

T2 - The Eleventh International Workshop on Ontology Matching

AU - Mohammadi, M.

AU - Hofman, Wout

AU - Tan, Yao Hua

N1 - Conference code: 11

PY - 2016

Y1 - 2016

N2 - This paper proposes statistical approaches to test if the difference between two ontology matchers is real. Specifically, the performances of the matchers over multiple data sets are obtained and based on their performances, the conclusion can be drawn whether one method is better than one another or not. To do so, the paired t-test and Wilcoxon signed rank test are proposed and the comparisons over six recently proposed methods are reported.

AB - This paper proposes statistical approaches to test if the difference between two ontology matchers is real. Specifically, the performances of the matchers over multiple data sets are obtained and based on their performances, the conclusion can be drawn whether one method is better than one another or not. To do so, the paired t-test and Wilcoxon signed rank test are proposed and the comparisons over six recently proposed methods are reported.

KW - Evaluation

KW - Ontology alignment

KW - Paired t-test

KW - Statistical inference

KW - Wilcoxon signed rank test

UR - http://resolver.tudelft.nl/uuid:38fd65d2-af37-49f5-97a4-69f5c7dd01d1

M3 - Poster

AN - SCOPUS:85009435131

SP - 231

EP - 232

Y2 - 18 October 2016

ER -

Ontology matching evaluation: A statistical perspective

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this