Efficient interactive query expansion with complete Search

Holger Bast, Debapriyo Majumdar, Ingmar Weber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Citations (Scopus)

Abstract

We present an efficient realization of the following interactive search engine feature: as the user is typing the query, words that are related to the last query word and that would lead to good hits are suggested, as well as selected such hits. The realization has three parts: (i) building clusters of related terms, (ii) adding this information as artificial words to the index such that (iii) the described feature reduces to an instance of prefix search and completion. An efficient solution for the latter is provided by the CompleteSearch engine, with which we have integrated the proposed feature. For building the clusters of related terms we propose a variant of latent semantic indexing that, unlike standard approaches, is completely transparent to the user. By experiments on two large test-collections, we demonstrate that the feature is provided at only a slight increase in query processing time and index size.

Original languageEnglish
Title of host publicationInternational Conference on Information and Knowledge Management, Proceedings
Pages857-860
Number of pages4
DOIs
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event16th ACM Conference on Information and Knowledge Management, CIKM 2007 - Lisboa, Portugal
Duration: 6 Nov 20079 Nov 2007

Other

Other16th ACM Conference on Information and Knowledge Management, CIKM 2007
CountryPortugal
CityLisboa
Period6/11/079/11/07

Fingerprint

Query expansion
Query
Integrated
Search engine
Query processing
Latent semantic indexing
Experiment
Test collections

Keywords

  • Index building
  • Interactive
  • Query expansion
  • Synsets
  • Wikipedia
  • Wordnet

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Bast, H., Majumdar, D., & Weber, I. (2007). Efficient interactive query expansion with complete Search. In International Conference on Information and Knowledge Management, Proceedings (pp. 857-860) https://doi.org/10.1145/1321440.1321560

Efficient interactive query expansion with complete Search. / Bast, Holger; Majumdar, Debapriyo; Weber, Ingmar.

International Conference on Information and Knowledge Management, Proceedings. 2007. p. 857-860.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bast, H, Majumdar, D & Weber, I 2007, Efficient interactive query expansion with complete Search. in International Conference on Information and Knowledge Management, Proceedings. pp. 857-860, 16th ACM Conference on Information and Knowledge Management, CIKM 2007, Lisboa, Portugal, 6/11/07. https://doi.org/10.1145/1321440.1321560
Bast H, Majumdar D, Weber I. Efficient interactive query expansion with complete Search. In International Conference on Information and Knowledge Management, Proceedings. 2007. p. 857-860 https://doi.org/10.1145/1321440.1321560
Bast, Holger ; Majumdar, Debapriyo ; Weber, Ingmar. / Efficient interactive query expansion with complete Search. International Conference on Information and Knowledge Management, Proceedings. 2007. pp. 857-860
@inproceedings{600e5ad0ba504e7eb2fc0349793095fe,
title = "Efficient interactive query expansion with complete Search",
abstract = "We present an efficient realization of the following interactive search engine feature: as the user is typing the query, words that are related to the last query word and that would lead to good hits are suggested, as well as selected such hits. The realization has three parts: (i) building clusters of related terms, (ii) adding this information as artificial words to the index such that (iii) the described feature reduces to an instance of prefix search and completion. An efficient solution for the latter is provided by the CompleteSearch engine, with which we have integrated the proposed feature. For building the clusters of related terms we propose a variant of latent semantic indexing that, unlike standard approaches, is completely transparent to the user. By experiments on two large test-collections, we demonstrate that the feature is provided at only a slight increase in query processing time and index size.",
keywords = "Index building, Interactive, Query expansion, Synsets, Wikipedia, Wordnet",
author = "Holger Bast and Debapriyo Majumdar and Ingmar Weber",
year = "2007",
month = "12",
day = "1",
doi = "10.1145/1321440.1321560",
language = "English",
isbn = "9781595938039",
pages = "857--860",
booktitle = "International Conference on Information and Knowledge Management, Proceedings",

}

TY - GEN

T1 - Efficient interactive query expansion with complete Search

AU - Bast, Holger

AU - Majumdar, Debapriyo

AU - Weber, Ingmar

PY - 2007/12/1

Y1 - 2007/12/1

N2 - We present an efficient realization of the following interactive search engine feature: as the user is typing the query, words that are related to the last query word and that would lead to good hits are suggested, as well as selected such hits. The realization has three parts: (i) building clusters of related terms, (ii) adding this information as artificial words to the index such that (iii) the described feature reduces to an instance of prefix search and completion. An efficient solution for the latter is provided by the CompleteSearch engine, with which we have integrated the proposed feature. For building the clusters of related terms we propose a variant of latent semantic indexing that, unlike standard approaches, is completely transparent to the user. By experiments on two large test-collections, we demonstrate that the feature is provided at only a slight increase in query processing time and index size.

AB - We present an efficient realization of the following interactive search engine feature: as the user is typing the query, words that are related to the last query word and that would lead to good hits are suggested, as well as selected such hits. The realization has three parts: (i) building clusters of related terms, (ii) adding this information as artificial words to the index such that (iii) the described feature reduces to an instance of prefix search and completion. An efficient solution for the latter is provided by the CompleteSearch engine, with which we have integrated the proposed feature. For building the clusters of related terms we propose a variant of latent semantic indexing that, unlike standard approaches, is completely transparent to the user. By experiments on two large test-collections, we demonstrate that the feature is provided at only a slight increase in query processing time and index size.

KW - Index building

KW - Interactive

KW - Query expansion

KW - Synsets

KW - Wikipedia

KW - Wordnet

UR - http://www.scopus.com/inward/record.url?scp=63449091915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63449091915&partnerID=8YFLogxK

U2 - 10.1145/1321440.1321560

DO - 10.1145/1321440.1321560

M3 - Conference contribution

SN - 9781595938039

SP - 857

EP - 860

BT - International Conference on Information and Knowledge Management, Proceedings

ER -