Object distinction: Distinguishing objects with identical names

Yin Xiaoxin; Han Jiawei; Gabrielle Dawn Allen

doi:10.1109/ICDE.2007.368983

Object distinction: Distinguishing objects with identical names

Yin Xiaoxin, Han Jiawei, Gabrielle Dawn Allen

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

Abstract

Different people or objects may share identical names in the real world, which causes confusion in many applications. It is a nontrivial task to distinguish those objects, especially when there is only very limited information associated with each of them. In this paper, we develop a general object distinction methodology called DISTINCT, which combines two complementary measures for relational similarity: set resemblance of neighbor tuples and random walk probability, and uses SVM to weigh different types of linkages without manually labeled training data. Experiments show that DISTINCT can accurately distinguish different objects with identical names in real databases.

Original language	English (US)
Title of host publication	23rd International Conference on Data Engineering, ICDE 2007
Publisher	IEEE Computer Society
Pages	1242-1246
Number of pages	5
ISBN (Print)	1424408032, 9781424408030
DOIs	https://doi.org/10.1109/ICDE.2007.368983
State	Published - 2007
Event	23rd International Conference on Data Engineering, ICDE 2007 - Istanbul, Turkey Duration: Apr 15 2007 → Apr 20 2007

Publication series

Name	Proceedings - International Conference on Data Engineering
ISSN (Print)	1084-4627

Other

Other	23rd International Conference on Data Engineering, ICDE 2007
Country/Territory	Turkey
City	Istanbul
Period	4/15/07 → 4/20/07

ASJC Scopus subject areas

Software
Signal Processing
Information Systems

Online availability

10.1109/ICDE.2007.368983

Library availability

Discover UIUC Full Text

Cite this

Object distinction: Distinguishing objects with identical names. / Xiaoxin, Yin; Jiawei, Han; Allen, Gabrielle Dawn.
23rd International Conference on Data Engineering, ICDE 2007. IEEE Computer Society, 2007. p. 1242-1246 4221773 (Proceedings - International Conference on Data Engineering).

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

Xiaoxin, Y, Jiawei, H & Allen, GD 2007, Object distinction: Distinguishing objects with identical names. in 23rd International Conference on Data Engineering, ICDE 2007., 4221773, Proceedings - International Conference on Data Engineering, IEEE Computer Society, pp. 1242-1246, 23rd International Conference on Data Engineering, ICDE 2007, Istanbul, Turkey, 4/15/07. https://doi.org/10.1109/ICDE.2007.368983

@inproceedings{97a8cb2cb5b64ba098a20ada9625ce48,

title = "Object distinction: Distinguishing objects with identical names",

abstract = "Different people or objects may share identical names in the real world, which causes confusion in many applications. It is a nontrivial task to distinguish those objects, especially when there is only very limited information associated with each of them. In this paper, we develop a general object distinction methodology called DISTINCT, which combines two complementary measures for relational similarity: set resemblance of neighbor tuples and random walk probability, and uses SVM to weigh different types of linkages without manually labeled training data. Experiments show that DISTINCT can accurately distinguish different objects with identical names in real databases.",

author = "Yin Xiaoxin and Han Jiawei and Allen, {Gabrielle Dawn}",

year = "2007",

doi = "10.1109/ICDE.2007.368983",

language = "English (US)",

isbn = "1424408032",

series = "Proceedings - International Conference on Data Engineering",

publisher = "IEEE Computer Society",

pages = "1242--1246",

booktitle = "23rd International Conference on Data Engineering, ICDE 2007",

note = "23rd International Conference on Data Engineering, ICDE 2007 ; Conference date: 15-04-2007 Through 20-04-2007",

}

TY - GEN

T1 - Object distinction

T2 - 23rd International Conference on Data Engineering, ICDE 2007

AU - Xiaoxin, Yin

AU - Jiawei, Han

AU - Allen, Gabrielle Dawn

PY - 2007

Y1 - 2007

N2 - Different people or objects may share identical names in the real world, which causes confusion in many applications. It is a nontrivial task to distinguish those objects, especially when there is only very limited information associated with each of them. In this paper, we develop a general object distinction methodology called DISTINCT, which combines two complementary measures for relational similarity: set resemblance of neighbor tuples and random walk probability, and uses SVM to weigh different types of linkages without manually labeled training data. Experiments show that DISTINCT can accurately distinguish different objects with identical names in real databases.

AB - Different people or objects may share identical names in the real world, which causes confusion in many applications. It is a nontrivial task to distinguish those objects, especially when there is only very limited information associated with each of them. In this paper, we develop a general object distinction methodology called DISTINCT, which combines two complementary measures for relational similarity: set resemblance of neighbor tuples and random walk probability, and uses SVM to weigh different types of linkages without manually labeled training data. Experiments show that DISTINCT can accurately distinguish different objects with identical names in real databases.

UR - http://www.scopus.com/inward/record.url?scp=34548791703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548791703&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2007.368983

DO - 10.1109/ICDE.2007.368983

M3 - Conference contribution

AN - SCOPUS:34548791703

SN - 1424408032

SN - 9781424408030

T3 - Proceedings - International Conference on Data Engineering

SP - 1242

EP - 1246

BT - 23rd International Conference on Data Engineering, ICDE 2007

PB - IEEE Computer Society

Y2 - 15 April 2007 through 20 April 2007

ER -

Object distinction: Distinguishing objects with identical names

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this