Visual Segmentation-Based Data Record Extraction From Web Documents

M. Weatherston; A. Obregon; Longzhuang Li; Yonghuai Liu

doi:10.1109/IRI.2007.4296670

Visual Segmentation-Based Data Record Extraction From Web Documents

M. Weatherston
, A. Obregon
, Longzhuang Li
, Yonghuai Liu

Adran Cyfrifiadureg

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion Cynhadledd › Trafodion Cynhadledd (ISBN)

29 Dyfyniadau (Scopus)

Crynodeb

Semi-structured data records contained in the Web pages provide useful information for shopping agents and metasearch engines. In this paper, we present a visual segmentation-based data record extraction (VSDR) method to extract data records from those Web pages. VSDR method first segments a Web page into semantic blocks using the spatial closeness and visual resemblance of data records, then neighboring and non-neighboring data records are extracted based on a compress and collapse technique. Experimental results slum that unlike the existing methods which only generate good results on their test domains, VSDR is a general data record extraction method that is able to produce quite stable and good results on a wide range of Web pages.

Iaith wreiddiol	Saesneg
Teitl	International Conference on Information Reuse and Itegration
Tudalennau	502-507
Nifer y tudalennau	6
ISBN (Electronig)	1-4244-1500-4
Dynodwyr Gwrthrych Digidol (DOIs)	https://doi.org/10.1109/IRI.2007.4296670
Statws	Cyhoeddwyd - 13 Awst 2007
Digwyddiad	International Conference on Information Reuse and Itegration - Las Vegas, Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon Hyd: 13 Awst 2007 → 15 Awst 2007

Cynhadledd

Cynhadledd	International Conference on Information Reuse and Itegration
Gwlad/Tiriogaeth	Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon
Dinas	Las Vegas
Cyfnod	13 Awst 2007 → 15 Awst 2007

Mynediad at Ddogfen

10.1109/IRI.2007.4296670

Cysylltiad parhaol

Dolen barhaus

Dyfynnu hyn

@inproceedings{e4d7544cabfb4a98a2cce2e3543a938b,

title = "Visual Segmentation-Based Data Record Extraction From Web Documents",

abstract = "Semi-structured data records contained in the Web pages provide useful information for shopping agents and metasearch engines. In this paper, we present a visual segmentation-based data record extraction (VSDR) method to extract data records from those Web pages. VSDR method first segments a Web page into semantic blocks using the spatial closeness and visual resemblance of data records, then neighboring and non-neighboring data records are extracted based on a compress and collapse technique. Experimental results slum that unlike the existing methods which only generate good results on their test domains, VSDR is a general data record extraction method that is able to produce quite stable and good results on a wide range of Web pages.",

author = "M. Weatherston and A. Obregon and Longzhuang Li and Yonghuai Liu",

note = "Li, Longzhuang, Liu, Yonghuai, Obregon, A., Weatherston, M. Visual Segmentation-Based Data Record Extraction From Web Documents. Proceedings of IEEE International Conference on Information Reuse and Integration, 2007, pp. 502-507. Sponsorship: IEEE; International Conference on Information Reuse and Itegration ; Conference date: 13-08-2007 Through 15-08-2007",

year = "2007",

month = aug,

day = "13",

doi = "10.1109/IRI.2007.4296670",

language = "English",

isbn = "1-4244-1500-4",

pages = "502--507",

booktitle = "International Conference on Information Reuse and Itegration",

}

Weatherston, M, Obregon, A, Li, L & Liu, Y 2007, Visual Segmentation-Based Data Record Extraction From Web Documents. yn International Conference on Information Reuse and Itegration. tt. 502-507, International Conference on Information Reuse and Itegration, Las Vegas, Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon, 13 Awst 2007. https://doi.org/10.1109/IRI.2007.4296670

TY - GEN

T1 - Visual Segmentation-Based Data Record Extraction From Web Documents

AU - Weatherston, M.

AU - Obregon, A.

AU - Li, Longzhuang

AU - Liu, Yonghuai

N1 - Li, Longzhuang, Liu, Yonghuai, Obregon, A., Weatherston, M. Visual Segmentation-Based Data Record Extraction From Web Documents. Proceedings of IEEE International Conference on Information Reuse and Integration, 2007, pp. 502-507. Sponsorship: IEEE

PY - 2007/8/13

Y1 - 2007/8/13

N2 - Semi-structured data records contained in the Web pages provide useful information for shopping agents and metasearch engines. In this paper, we present a visual segmentation-based data record extraction (VSDR) method to extract data records from those Web pages. VSDR method first segments a Web page into semantic blocks using the spatial closeness and visual resemblance of data records, then neighboring and non-neighboring data records are extracted based on a compress and collapse technique. Experimental results slum that unlike the existing methods which only generate good results on their test domains, VSDR is a general data record extraction method that is able to produce quite stable and good results on a wide range of Web pages.

AB - Semi-structured data records contained in the Web pages provide useful information for shopping agents and metasearch engines. In this paper, we present a visual segmentation-based data record extraction (VSDR) method to extract data records from those Web pages. VSDR method first segments a Web page into semantic blocks using the spatial closeness and visual resemblance of data records, then neighboring and non-neighboring data records are extracted based on a compress and collapse technique. Experimental results slum that unlike the existing methods which only generate good results on their test domains, VSDR is a general data record extraction method that is able to produce quite stable and good results on a wide range of Web pages.

U2 - 10.1109/IRI.2007.4296670

DO - 10.1109/IRI.2007.4296670

M3 - Conference Proceeding (ISBN)

SN - 1-4244-1500-4

SP - 502

EP - 507

BT - International Conference on Information Reuse and Itegration

T2 - International Conference on Information Reuse and Itegration

Y2 - 13 August 2007 through 15 August 2007

ER -

Visual Segmentation-Based Data Record Extraction From Web Documents

Crynodeb

Cynhadledd

Mynediad at Ddogfen

Cysylltiad parhaol

Ôl bys

Dyfynnu hyn