Improving record matching in imprecise and uncertain datasets

David Croft

Research output: Contribution to journalArticle

Abstract

Museum collections represent a highly challenging search space. This article proposes a novel approach for co-referent record identification which is suitable for use across multiple separate collections. The proposed approach is intended to be suitable for use despite highly imprecise/uncertain attribute values in the records. It is hoped that this can be achieved through a combination of aspects from the fields of probabillistic record linkage, document classification, and fuzzy clustering.
Original languageEnglish
Pages (from-to)347-354
Number of pages8
JournalLiterary and linguistic computing
Volume27
Issue number4
DOIs
Publication statusPublished - 2012

Fingerprint

Fuzzy clustering
Museums

Cite this

Improving record matching in imprecise and uncertain datasets. / Croft, David.

In: Literary and linguistic computing, Vol. 27, No. 4, 2012, p. 347-354.

Research output: Contribution to journalArticle

@article{d0f4559c8200492dafbd3cb0da65d103,
title = "Improving record matching in imprecise and uncertain datasets",
abstract = "Museum collections represent a highly challenging search space. This article proposes a novel approach for co-referent record identification which is suitable for use across multiple separate collections. The proposed approach is intended to be suitable for use despite highly imprecise/uncertain attribute values in the records. It is hoped that this can be achieved through a combination of aspects from the fields of probabillistic record linkage, document classification, and fuzzy clustering.",
author = "David Croft",
year = "2012",
doi = "10.1093/llc/fqs028",
language = "English",
volume = "27",
pages = "347--354",
journal = "Literary and linguistic computing",
publisher = "ALLC",
number = "4",

}

TY - JOUR

T1 - Improving record matching in imprecise and uncertain datasets

AU - Croft, David

PY - 2012

Y1 - 2012

N2 - Museum collections represent a highly challenging search space. This article proposes a novel approach for co-referent record identification which is suitable for use across multiple separate collections. The proposed approach is intended to be suitable for use despite highly imprecise/uncertain attribute values in the records. It is hoped that this can be achieved through a combination of aspects from the fields of probabillistic record linkage, document classification, and fuzzy clustering.

AB - Museum collections represent a highly challenging search space. This article proposes a novel approach for co-referent record identification which is suitable for use across multiple separate collections. The proposed approach is intended to be suitable for use despite highly imprecise/uncertain attribute values in the records. It is hoped that this can be achieved through a combination of aspects from the fields of probabillistic record linkage, document classification, and fuzzy clustering.

U2 - 10.1093/llc/fqs028

DO - 10.1093/llc/fqs028

M3 - Article

VL - 27

SP - 347

EP - 354

JO - Literary and linguistic computing

JF - Literary and linguistic computing

IS - 4

ER -