Retrieving Web Pages using Content, Links, URLs and Anchors

T.H.W. Westerveld; Wessel Kraaij; Djoerd Hiemstra

Retrieving Web Pages using Content, Links, URLs and Anchors

T.H.W. Westerveld, Wessel Kraaij, Djoerd Hiemstra

Databases (Former)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

77 Downloads (Pure)

Abstract

For this year’s web track, we concentrated on the entry page finding task. For the content-only runs, in both the ad-hoc task and the entry page finding task, we used an information retrieval system based on a simple unigram language model. In the Ad hoc task we experimented with alternatieve approaches to smoothing. For the entry page task, we incorporated additional information into the model. The sources of information we used in addition to the document’s content are links, URLs and anchors. We found that almost every approach can improve the results of a content only run. In the end, a very basic approach, using the depth of the path of the URL as a prior, yielded by far the largest improvement over the content only results.

Original language	English
Title of host publication	Proceedings of the Tenth Text REtrieval Conference (TREC 2001)
Editors	E.M Voorhees, D.K. Harman
Place of Publication	Gaithersburg, Maryland, USA
Publisher	National Institute for Science and Technology (NIST)
Pages	663-672
Number of pages	10
Publication status	Published - 2002
Event	Tenth Text REtrieval Conference, TREC-10 2001 - Gaithersburg, United States Duration: 13 Nov 2001 → 16 Nov 2001 Conference number: 10

Publication series

Name	NIST Special Publication
Publisher	National Institute for Science and Technology (NIST)
Number	500-250
Volume	SP 500

Conference

Conference	Tenth Text REtrieval Conference, TREC-10 2001
Abbreviated title	TREC
Country	United States
City	Gaithersburg
Period	13/11/01 → 16/11/01

Keywords

DB-IR: INFORMATION RETRIEVAL
EWI-7365
METIS-204321
IR-66475

Access to Document

TNO-UTwente-trec10-final
open
TNO-UTwente-trec10-final
open

http://trec.nist.gov/pubs/trec10/t10_proceedings.html

Fingerprint Dive into the research topics of 'Retrieving Web Pages using Content, Links, URLs and Anchors'. Together they form a unique fingerprint.

Cite this

Westerveld, T. H. W., Kraaij, W., & Hiemstra, D. (2002). Retrieving Web Pages using Content, Links, URLs and Anchors. In E. M. Voorhees, & D. K. Harman (Eds.), Proceedings of the Tenth Text REtrieval Conference (TREC 2001) (pp. 663-672). (NIST Special Publication; Vol. SP 500, No. 500-250). National Institute for Science and Technology (NIST). http://trec.nist.gov/pubs/trec10/t10_proceedings.html

@inproceedings{87e21d80e45e4e2daff608f19bae609a,

title = "Retrieving Web Pages using Content, Links, URLs and Anchors",

abstract = "For this year{\textquoteright}s web track, we concentrated on the entry page finding task. For the content-only runs, in both the ad-hoc task and the entry page finding task, we used an information retrieval system based on a simple unigram language model. In the Ad hoc task we experimented with alternatieve approaches to smoothing. For the entry page task, we incorporated additional information into the model. The sources of information we used in addition to the document{\textquoteright}s content are links, URLs and anchors. We found that almost every approach can improve the results of a content only run. In the end, a very basic approach, using the depth of the path of the URL as a prior, yielded by far the largest improvement over the content only results.",

keywords = "DB-IR: INFORMATION RETRIEVAL, EWI-7365, METIS-204321, IR-66475",

author = "T.H.W. Westerveld and Wessel Kraaij and Djoerd Hiemstra",

note = "Imported from EWI/DB PMS [db-utwente:inpr:0000003205]; Tenth Text REtrieval Conference, TREC-10 2001, TREC ; Conference date: 13-11-2001 Through 16-11-2001",

year = "2002",

language = "English",

series = "NIST Special Publication",

publisher = "National Institute for Science and Technology (NIST)",

number = "500-250",

pages = "663--672",

editor = "E.M Voorhees and D.K. Harman",

booktitle = "Proceedings of the Tenth Text REtrieval Conference (TREC 2001)",

}

Westerveld, THW, Kraaij, W & Hiemstra, D 2002, Retrieving Web Pages using Content, Links, URLs and Anchors. in EM Voorhees & DK Harman (eds), Proceedings of the Tenth Text REtrieval Conference (TREC 2001). NIST Special Publication, no. 500-250, vol. SP 500, National Institute for Science and Technology (NIST), Gaithersburg, Maryland, USA, pp. 663-672, Tenth Text REtrieval Conference, TREC-10 2001, Gaithersburg, United States, 13/11/01. <http://trec.nist.gov/pubs/trec10/t10_proceedings.html>

Retrieving Web Pages using Content, Links, URLs and Anchors. / Westerveld, T.H.W.; Kraaij, Wessel; Hiemstra, Djoerd.

Proceedings of the Tenth Text REtrieval Conference (TREC 2001). ed. / E.M Voorhees; D.K. Harman. Gaithersburg, Maryland, USA : National Institute for Science and Technology (NIST), 2002. p. 663-672 (NIST Special Publication; Vol. SP 500, No. 500-250).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Retrieving Web Pages using Content, Links, URLs and Anchors

AU - Westerveld, T.H.W.

AU - Kraaij, Wessel

AU - Hiemstra, Djoerd

N1 - Conference code: 10

PY - 2002

Y1 - 2002

N2 - For this year’s web track, we concentrated on the entry page finding task. For the content-only runs, in both the ad-hoc task and the entry page finding task, we used an information retrieval system based on a simple unigram language model. In the Ad hoc task we experimented with alternatieve approaches to smoothing. For the entry page task, we incorporated additional information into the model. The sources of information we used in addition to the document’s content are links, URLs and anchors. We found that almost every approach can improve the results of a content only run. In the end, a very basic approach, using the depth of the path of the URL as a prior, yielded by far the largest improvement over the content only results.

AB - For this year’s web track, we concentrated on the entry page finding task. For the content-only runs, in both the ad-hoc task and the entry page finding task, we used an information retrieval system based on a simple unigram language model. In the Ad hoc task we experimented with alternatieve approaches to smoothing. For the entry page task, we incorporated additional information into the model. The sources of information we used in addition to the document’s content are links, URLs and anchors. We found that almost every approach can improve the results of a content only run. In the end, a very basic approach, using the depth of the path of the URL as a prior, yielded by far the largest improvement over the content only results.

KW - DB-IR: INFORMATION RETRIEVAL

KW - EWI-7365

KW - METIS-204321

KW - IR-66475

M3 - Conference contribution

T3 - NIST Special Publication

SP - 663

EP - 672

BT - Proceedings of the Tenth Text REtrieval Conference (TREC 2001)

A2 - Voorhees, E.M

A2 - Harman, D.K.

PB - National Institute for Science and Technology (NIST)

CY - Gaithersburg, Maryland, USA

T2 - Tenth Text REtrieval Conference, TREC-10 2001

Y2 - 13 November 2001 through 16 November 2001

ER -