Using local optimality criteria for efficient information retrieval with redundant information filters

@article{Rowe1996UsingLO,
  title={Using local optimality criteria for efficient information retrieval with redundant information filters},
  author={Neil C. Rowe},
  journal={ArXiv},
  year={1996},
  volume={cs.IR/9809121}
}
  • N. Rowe
  • Published 1 April 1996
  • Computer Science
  • ArXiv
We consider information retrieval when the data—for instance, multimedia—is computationally expensive to fetch. Our approach uses “information filters” to considerably narrow the universe of possibilities before retrieval. We are especially interested in redundant information filters that save time over more general but more costly filters. Efficient retrieval requires that decisions must be made about the necessity, order, and concurrent processing of proposed filters (an “execution plan”). We… 

Load Balancing of Parallelized Information Filters

TLDR
An analytic model for the costs and advantages of load rebalancing for the parallel filtering processes, as well as a quick heuristic for its desirability, are developed and results show that the proposed heuristic rebalance criterion gives close to optimal balancing.

Waqs: a web-based approximate query system

TLDR
A new technique for document retrieval on the Web is presented, designed to allow a detailed retrieval and hence reduce the amount of matches returned by typical search engines.

Automatically Determining Semantics for World Wide Web Multimedia Information Retrieval

TLDR
The problems in determining the semantics of images on the WWW and the approach of AMORE, a WWW search engine that is developed and whose techniques can be extended to other media like audio and video are described.

AMORE: a world-wide web image retrieval engine

TLDR
AMORE is a World-Wide Web image retrieval engine integrating several techniques to facilitate effective retrieval of images from the Web and believes that the integration of information retrieval with visualization is helpful for the user's retrieval tasks.

AMORE: A World Wide Web image retrieval engine

TLDR
This paper presents AMORE's user interface and explains the technique for retrieving images visually similar to a user specified image, and develops a Query Result Visualization Environment that allows the organization of the results if many images are retrieved.

Exploiting Captions for Web Data Mining by Neil C. Rowe

TLDR
While it is hard, classes of mapping schemes are distinguishable, and segmentation of the media can be matched to a parsing of the caption by constraint-satisfaction methods, active work is addressing the issue of automatically learning the clues for mapping from examples.

Exploiting Captions for Web Data Mining

TLDR
This chapter surveys research on using captions in data mining from the Web, and discusses the range of syntactic clues (such as HTML tags) and semantic clues ( such as particular words) and how to quantify clue strength and combine clues for a consensus.

Precise and Efficient Retrieval of Captioned Images: The MARIE Project

  • N. Rowe
  • Computer Science
    Libr. Trends
  • 1999
TLDR
Experiments show MARIE prototypes are more accurate than simpler methods, although the task is very challenging and more work is needed, and its processing is illustrated in detail on part of an Internet World Wide Web page.

Finding Photograph Captions Multimodally on the World Wide Web

TLDR
This work presents a relatively simple way to index photographs by localizing their likely explicit and implicit captions with a kind of expert system that avoids full image processing and full natural-language processing, and can thus serve as a preliminary filtering for such detailed content analysis.

Automatic classification of objects in captioned depictive photographs for retrieval

This article is Chapter 4 in Intelligent Multimedia Information Retrieval, ed. M. Maybury, pp. 65-79, Cambridge, MA: AAAI Press, 1997

References

SHOWING 1-10 OF 40 REFERENCES

Query Optimization in Database Systems

TLDR
These methods are presented in the framework of a general query evaluation procedure using the relational calculus representation of queries, and nonstandard query optimization issues such as higher level query evaluation, query optimization in distributed databases, and use of database machines are addressed.

Ordering Conjunctive Queries

A formal model of trade-off between optimization and execution costs in semantic query optimization

Knowledge organization and access in a conceptual information system

  • L. F. Rau
  • Computer Science
    Inf. Process. Manag.
  • 1987

An optimal evaluation of Boolean expressions in an online query system

A method is given for a fast evaluation of a Boolean expression of attributes against a record of a file, and it thus enables a faster response to general queries for reports from a data bank stored

Lexical ambiguity and information retrieval

TLDR
An analysis of lexical ambiguity in information retrieval test collections and experiments to determine the utility of word meanings for separating relevant from nonrelevant documents show that there is considerable ambiguity even in a specialized database.

Exploiting Captions in Retrieval of Multimedia Data

Progress in the Application of Natural Language Processing to Information Retrieval Tasks

TLDR
This paper will examine and review recent progress in using the lexical, syntactic, semantic and discourse levels of the language analysis for tasks like automatic and semi-automatic indexing of text, text retrieval, text abstracting and summarisation, thesaurus generation from text corpus and conceptual information retrieval.

Knowledge-based search tactics for an intelligent intermediary system

TLDR
This paper focuses on the two central concepts behind EP-X: semantically based search and knowledge-based search tactics, which uses such tactics to actively assist users in defining or refining their topics of interest.

Query processing in a multimedia document system

TLDR
Query processing in a multimedia document system is described, with focus on the storage organization in which both optical and magnetic devices can coexist.