Browsing for information by highlighting automatically generated annotations: a user study and evaluation

Victoria Uren; Enrico Motta; Martin Dzbor; Philipp Cimiano

doi:10.1145/1088622.1088637

Browsing for information by highlighting automatically generated annotations: a user study and evaluation

Victoria Uren, Enrico Motta, Martin Dzbor, Philipp Cimiano

Operations & Information Management

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

The realization of the Semantic Web is constrained by a knowledge acquisition bottleneck, i.e. the problem of how to add RDF mark-up to the millions of ordinary web pages that already exist. Information Extraction (IE) has been proposed as a solution to the annotation bottleneck. In the task based evaluation reported here, we compared the performance of users without access to annotation, users working with annotations which had been produced from manually constructed knowledge bases, and users working with annotations augmented using IE. We looked at retrieval performance, overlap between retrieved items and the two sets of annotations, and usage of annotation options. Automatically generated annotations were found to add value to the browsing experience in the scenario investigated.

Original language	English
Title of host publication	Proceedings of the 3rd international conference on knowledge capture - K-CAP '05
Place of Publication	New York, NY (US)
Publisher	ACM
Pages	75-82
Number of pages	8
ISBN (Print)	1-59593-163-5
DOIs	https://doi.org/10.1145/1088622.1088637
Publication status	Published - 2 Oct 2005
Event	3rd international conference on Knowledge capture - Alberta, Canada Duration: 2 Oct 2005 → 5 Oct 2005

Conference

Conference	3rd international conference on Knowledge capture
Abbreviated title	K-CAP'05
Country/Territory	Canada
City	Alberta
Period	2/10/05 → 5/10/05

Access to Document

10.1145/1088622.1088637

Cite this

@inproceedings{8f1976833d894a3dbd655d1844a8b87f,

title = "Browsing for information by highlighting automatically generated annotations: a user study and evaluation",

abstract = "The realization of the Semantic Web is constrained by a knowledge acquisition bottleneck, i.e. the problem of how to add RDF mark-up to the millions of ordinary web pages that already exist. Information Extraction (IE) has been proposed as a solution to the annotation bottleneck. In the task based evaluation reported here, we compared the performance of users without access to annotation, users working with annotations which had been produced from manually constructed knowledge bases, and users working with annotations augmented using IE. We looked at retrieval performance, overlap between retrieved items and the two sets of annotations, and usage of annotation options. Automatically generated annotations were found to add value to the browsing experience in the scenario investigated.",

author = "Victoria Uren and Enrico Motta and Martin Dzbor and Philipp Cimiano",

year = "2005",

month = oct,

day = "2",

doi = "10.1145/1088622.1088637",

language = "English",

isbn = "1-59593-163-5",

pages = "75--82",

booktitle = "Proceedings of the 3rd international conference on knowledge capture - K-CAP '05",

publisher = "ACM",

address = "United States",

note = "3rd international conference on Knowledge capture, K-CAP'05 ; Conference date: 02-10-2005 Through 05-10-2005",

}

Uren, V, Motta, E, Dzbor, M & Cimiano, P 2005, Browsing for information by highlighting automatically generated annotations: a user study and evaluation. in Proceedings of the 3rd international conference on knowledge capture - K-CAP '05. ACM, New York, NY (US), pp. 75-82, 3rd international conference on Knowledge capture, Alberta, Canada, 2/10/05. https://doi.org/10.1145/1088622.1088637

TY - GEN

T1 - Browsing for information by highlighting automatically generated annotations

T2 - 3rd international conference on Knowledge capture

AU - Uren, Victoria

AU - Motta, Enrico

AU - Dzbor, Martin

AU - Cimiano, Philipp

PY - 2005/10/2

Y1 - 2005/10/2

N2 - The realization of the Semantic Web is constrained by a knowledge acquisition bottleneck, i.e. the problem of how to add RDF mark-up to the millions of ordinary web pages that already exist. Information Extraction (IE) has been proposed as a solution to the annotation bottleneck. In the task based evaluation reported here, we compared the performance of users without access to annotation, users working with annotations which had been produced from manually constructed knowledge bases, and users working with annotations augmented using IE. We looked at retrieval performance, overlap between retrieved items and the two sets of annotations, and usage of annotation options. Automatically generated annotations were found to add value to the browsing experience in the scenario investigated.

AB - The realization of the Semantic Web is constrained by a knowledge acquisition bottleneck, i.e. the problem of how to add RDF mark-up to the millions of ordinary web pages that already exist. Information Extraction (IE) has been proposed as a solution to the annotation bottleneck. In the task based evaluation reported here, we compared the performance of users without access to annotation, users working with annotations which had been produced from manually constructed knowledge bases, and users working with annotations augmented using IE. We looked at retrieval performance, overlap between retrieved items and the two sets of annotations, and usage of annotation options. Automatically generated annotations were found to add value to the browsing experience in the scenario investigated.

UR - http://www.scopus.com/inward/record.url?scp=77952325578&partnerID=8YFLogxK

UR - http://dl.acm.org/citation.cfm?doid=1088622.1088637

U2 - 10.1145/1088622.1088637

DO - 10.1145/1088622.1088637

M3 - Conference publication

AN - SCOPUS:77952325578

SN - 1-59593-163-5

SP - 75

EP - 82

BT - Proceedings of the 3rd international conference on knowledge capture - K-CAP '05

PB - ACM

CY - New York, NY (US)

Y2 - 2 October 2005 through 5 October 2005

ER -

Browsing for information by highlighting automatically generated annotations: a user study and evaluation

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Extracting significant words from corpora for ontology extraction

Cite this