Query suggestions in the absence of query logs

Sumit Bhatia, Debapriyo Majumdar, Prasenjit Mitra

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

95 Citations (Scopus)

Abstract

After an end-user has partially input a query, intelligent search engines can suggest possible completions of the partial query to help end-users quickly express their information needs. All major web-search engines and most proposed methods that suggest queries rely on search engine query logs to determine possible query suggestions. However, for customized search systems in the enterprise domain, intranet search, or personalized search such as email or desktop search or for infrequent queries, query logs are either not available or the user base and the number of past user queries is too small to learn appropriate models. We propose a probabilistic mechanism for generating query suggestions from the corpus without using query logs. We utilize the document corpus to extract a set of candidate phrases. As soon as a user starts typing a query, phrases that are highly correlated with the partial user query are selected as completions of the partial query and are offered as query suggestions. Our proposed approach is tested on a variety of datasets and is compared with state-of-the-art approaches. The experimental results clearly demonstrate the effectiveness of our approach in suggesting queries with higher quality.

Original languageEnglish
Title of host publicationSIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval
Pages795-804
Number of pages10
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'11 - Beijing
Duration: 24 Jul 201128 Jul 2011

Other

Other34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'11
CityBeijing
Period24/7/1128/7/11

Fingerprint

Search engines
Intranets
Electronic mail
Industry

Keywords

  • Enterprise search
  • Query completion
  • Query formulation
  • Query log analysis
  • Query suggestion

ASJC Scopus subject areas

  • Information Systems

Cite this

Bhatia, S., Majumdar, D., & Mitra, P. (2011). Query suggestions in the absence of query logs. In SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 795-804) https://doi.org/10.1145/2009916.2010023

Query suggestions in the absence of query logs. / Bhatia, Sumit; Majumdar, Debapriyo; Mitra, Prasenjit.

SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011. p. 795-804.

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

Bhatia, S, Majumdar, D & Mitra, P 2011, Query suggestions in the absence of query logs. in SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 795-804, 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'11, Beijing, 24/7/11. https://doi.org/10.1145/2009916.2010023
Bhatia S, Majumdar D, Mitra P. Query suggestions in the absence of query logs. In SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011. p. 795-804 https://doi.org/10.1145/2009916.2010023
Bhatia, Sumit ; Majumdar, Debapriyo ; Mitra, Prasenjit. / Query suggestions in the absence of query logs. SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011. pp. 795-804
@inproceedings{fce6ed29d2e24182a8c9781723d12a56,
title = "Query suggestions in the absence of query logs",
abstract = "After an end-user has partially input a query, intelligent search engines can suggest possible completions of the partial query to help end-users quickly express their information needs. All major web-search engines and most proposed methods that suggest queries rely on search engine query logs to determine possible query suggestions. However, for customized search systems in the enterprise domain, intranet search, or personalized search such as email or desktop search or for infrequent queries, query logs are either not available or the user base and the number of past user queries is too small to learn appropriate models. We propose a probabilistic mechanism for generating query suggestions from the corpus without using query logs. We utilize the document corpus to extract a set of candidate phrases. As soon as a user starts typing a query, phrases that are highly correlated with the partial user query are selected as completions of the partial query and are offered as query suggestions. Our proposed approach is tested on a variety of datasets and is compared with state-of-the-art approaches. The experimental results clearly demonstrate the effectiveness of our approach in suggesting queries with higher quality.",
keywords = "Enterprise search, Query completion, Query formulation, Query log analysis, Query suggestion",
author = "Sumit Bhatia and Debapriyo Majumdar and Prasenjit Mitra",
year = "2011",
doi = "10.1145/2009916.2010023",
language = "English",
isbn = "9781450309349",
pages = "795--804",
booktitle = "SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval",

}

TY - GEN

T1 - Query suggestions in the absence of query logs

AU - Bhatia, Sumit

AU - Majumdar, Debapriyo

AU - Mitra, Prasenjit

PY - 2011

Y1 - 2011

N2 - After an end-user has partially input a query, intelligent search engines can suggest possible completions of the partial query to help end-users quickly express their information needs. All major web-search engines and most proposed methods that suggest queries rely on search engine query logs to determine possible query suggestions. However, for customized search systems in the enterprise domain, intranet search, or personalized search such as email or desktop search or for infrequent queries, query logs are either not available or the user base and the number of past user queries is too small to learn appropriate models. We propose a probabilistic mechanism for generating query suggestions from the corpus without using query logs. We utilize the document corpus to extract a set of candidate phrases. As soon as a user starts typing a query, phrases that are highly correlated with the partial user query are selected as completions of the partial query and are offered as query suggestions. Our proposed approach is tested on a variety of datasets and is compared with state-of-the-art approaches. The experimental results clearly demonstrate the effectiveness of our approach in suggesting queries with higher quality.

AB - After an end-user has partially input a query, intelligent search engines can suggest possible completions of the partial query to help end-users quickly express their information needs. All major web-search engines and most proposed methods that suggest queries rely on search engine query logs to determine possible query suggestions. However, for customized search systems in the enterprise domain, intranet search, or personalized search such as email or desktop search or for infrequent queries, query logs are either not available or the user base and the number of past user queries is too small to learn appropriate models. We propose a probabilistic mechanism for generating query suggestions from the corpus without using query logs. We utilize the document corpus to extract a set of candidate phrases. As soon as a user starts typing a query, phrases that are highly correlated with the partial user query are selected as completions of the partial query and are offered as query suggestions. Our proposed approach is tested on a variety of datasets and is compared with state-of-the-art approaches. The experimental results clearly demonstrate the effectiveness of our approach in suggesting queries with higher quality.

KW - Enterprise search

KW - Query completion

KW - Query formulation

KW - Query log analysis

KW - Query suggestion

UR - http://www.scopus.com/inward/record.url?scp=80052119355&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052119355&partnerID=8YFLogxK

U2 - 10.1145/2009916.2010023

DO - 10.1145/2009916.2010023

M3 - Conference contribution

SN - 9781450309349

SP - 795

EP - 804

BT - SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval

ER -