Retrieving documents by plausible inference

A preliminary study

W. B. Croft, T. J. Lucia, Paul R Cohen

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

18 Citations (Scopus)

Abstract

Choosing an appropriate document representation and search strategy for document retrieval has been largely guided by achieving good average performance instead of optimizing the results for each individual query. A model of retrieval based on plausible inference gives us a different perspective and suggests that techniques should be found for combining multiple sources of evidence (or search strategies) into an overall assessment of a document's relevance, rather than attempting to pick a single strategy. In this paper, we explain our approach to plausible inference for retrieval and describe some preliminary experiments designed to test this approach. The experiments use a spreading activation search to implement the plausible inference process. The results show that significant effectiveness improvements are possible using this approach.

Original languageEnglish (US)
Title of host publicationProceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988
PublisherAssociation for Computing Machinery, Inc
Pages481-494
Number of pages14
ISBN (Electronic)2706103094, 9782706103094
DOIs
StatePublished - May 1 1988
Externally publishedYes
Event11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988 - Grenoble, France
Duration: Jun 13 1988Jun 15 1988

Other

Other11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988
CountryFrance
CityGrenoble
Period6/13/886/15/88

Fingerprint

Experiments
Chemical activation

ASJC Scopus subject areas

  • Information Systems

Cite this

Croft, W. B., Lucia, T. J., & Cohen, P. R. (1988). Retrieving documents by plausible inference: A preliminary study. In Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988 (pp. 481-494). Association for Computing Machinery, Inc. https://doi.org/10.1145/62437.62491

Retrieving documents by plausible inference : A preliminary study. / Croft, W. B.; Lucia, T. J.; Cohen, Paul R.

Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988. Association for Computing Machinery, Inc, 1988. p. 481-494.

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

Croft, WB, Lucia, TJ & Cohen, PR 1988, Retrieving documents by plausible inference: A preliminary study. in Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988. Association for Computing Machinery, Inc, pp. 481-494, 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988, Grenoble, France, 6/13/88. https://doi.org/10.1145/62437.62491
Croft WB, Lucia TJ, Cohen PR. Retrieving documents by plausible inference: A preliminary study. In Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988. Association for Computing Machinery, Inc. 1988. p. 481-494 https://doi.org/10.1145/62437.62491
Croft, W. B. ; Lucia, T. J. ; Cohen, Paul R. / Retrieving documents by plausible inference : A preliminary study. Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988. Association for Computing Machinery, Inc, 1988. pp. 481-494
@inproceedings{5dc918db89014d54928f22adf2743f7e,
title = "Retrieving documents by plausible inference: A preliminary study",
abstract = "Choosing an appropriate document representation and search strategy for document retrieval has been largely guided by achieving good average performance instead of optimizing the results for each individual query. A model of retrieval based on plausible inference gives us a different perspective and suggests that techniques should be found for combining multiple sources of evidence (or search strategies) into an overall assessment of a document's relevance, rather than attempting to pick a single strategy. In this paper, we explain our approach to plausible inference for retrieval and describe some preliminary experiments designed to test this approach. The experiments use a spreading activation search to implement the plausible inference process. The results show that significant effectiveness improvements are possible using this approach.",
author = "Croft, {W. B.} and Lucia, {T. J.} and Cohen, {Paul R}",
year = "1988",
month = "5",
day = "1",
doi = "10.1145/62437.62491",
language = "English (US)",
pages = "481--494",
booktitle = "Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Retrieving documents by plausible inference

T2 - A preliminary study

AU - Croft, W. B.

AU - Lucia, T. J.

AU - Cohen, Paul R

PY - 1988/5/1

Y1 - 1988/5/1

N2 - Choosing an appropriate document representation and search strategy for document retrieval has been largely guided by achieving good average performance instead of optimizing the results for each individual query. A model of retrieval based on plausible inference gives us a different perspective and suggests that techniques should be found for combining multiple sources of evidence (or search strategies) into an overall assessment of a document's relevance, rather than attempting to pick a single strategy. In this paper, we explain our approach to plausible inference for retrieval and describe some preliminary experiments designed to test this approach. The experiments use a spreading activation search to implement the plausible inference process. The results show that significant effectiveness improvements are possible using this approach.

AB - Choosing an appropriate document representation and search strategy for document retrieval has been largely guided by achieving good average performance instead of optimizing the results for each individual query. A model of retrieval based on plausible inference gives us a different perspective and suggests that techniques should be found for combining multiple sources of evidence (or search strategies) into an overall assessment of a document's relevance, rather than attempting to pick a single strategy. In this paper, we explain our approach to plausible inference for retrieval and describe some preliminary experiments designed to test this approach. The experiments use a spreading activation search to implement the plausible inference process. The results show that significant effectiveness improvements are possible using this approach.

UR - http://www.scopus.com/inward/record.url?scp=33745798353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745798353&partnerID=8YFLogxK

U2 - 10.1145/62437.62491

DO - 10.1145/62437.62491

M3 - Conference contribution

SP - 481

EP - 494

BT - Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1988

PB - Association for Computing Machinery, Inc

ER -