Using summaries in document retrieval

Authors:
Mark Wasson
Affiliations:
LexisNexis, Miamisburg, OH
Venue:
AS '02 Proceedings of the ACL-02 Workshop on Automatic Summarization - Volume 4
Year:
2002

Citing 6
Cited 3

Query expansion using lexical-semantic relations

SIGIR '94 Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval
Automatic condensation of electronic publications by sentence selection

Information Processing and Management: an International Journal - Special issue: summarizing text
Detection of shifts in user interests for personalized information filtering

SIGIR '96 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval
Generic summaries for indexing in information retrieval

Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Large-scale controlled vocabulary indexing for named entities

ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Using leading text for news summaries: evaluation results and implications for commercial summarization applications

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2

Mobile content enrichment

Proceedings of the 12th international conference on Intelligent user interfaces
Automatic summarising: The state of the art

Information Processing and Management: an International Journal
Summarization of compressed text images: an experience on Indic script documents

Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper examines the role that summaries can play in document retrieval. Thirty searches are applied to full-text and summaries only in large document collections, and the results are evaluated using two different evaluation scopes. The results support the view that those customer segments who want smaller answer sets focused on highly relevant documents benefit from limiting their searches to summaries. On the other hand, those customer segments who wish to retrieve all references to some topic should continue to search full-text.