A Method for Taking Source Overlap into Account While Querying Text Collection

Research output: Patent

Abstract

Existing algorithms for collection selection make the assumption that all collections are disjoint. This is an unrealistic assumption in most scenarios. Consequently, in practice, the existing approaches are liable to access sources that do not return any new (not yet seen) answers. Our approach combines relevance as well as inter-source overlap information to provide significantly better collection selection capability. The crux of our invention is an efficient way of estimating the overlap statistics between collections and using this effectively combining this information in collection selection.
Original languageEnglish (US)
StatePublished - Mar 11 2005

Fingerprint

Patents and inventions
Statistics

Cite this

@misc{ddedfd97bec14aa8971f893aeb7621f7,
title = "A Method for Taking Source Overlap into Account While Querying Text Collection",
abstract = "Existing algorithms for collection selection make the assumption that all collections are disjoint. This is an unrealistic assumption in most scenarios. Consequently, in practice, the existing approaches are liable to access sources that do not return any new (not yet seen) answers. Our approach combines relevance as well as inter-source overlap information to provide significantly better collection selection capability. The crux of our invention is an efficient way of estimating the overlap statistics between collections and using this effectively combining this information in collection selection.",
author = "Subbarao Kambhampati",
year = "2005",
month = "3",
day = "11",
language = "English (US)",
type = "Patent",

}

TY - PAT

T1 - A Method for Taking Source Overlap into Account While Querying Text Collection

AU - Kambhampati, Subbarao

PY - 2005/3/11

Y1 - 2005/3/11

N2 - Existing algorithms for collection selection make the assumption that all collections are disjoint. This is an unrealistic assumption in most scenarios. Consequently, in practice, the existing approaches are liable to access sources that do not return any new (not yet seen) answers. Our approach combines relevance as well as inter-source overlap information to provide significantly better collection selection capability. The crux of our invention is an efficient way of estimating the overlap statistics between collections and using this effectively combining this information in collection selection.

AB - Existing algorithms for collection selection make the assumption that all collections are disjoint. This is an unrealistic assumption in most scenarios. Consequently, in practice, the existing approaches are liable to access sources that do not return any new (not yet seen) answers. Our approach combines relevance as well as inter-source overlap information to provide significantly better collection selection capability. The crux of our invention is an efficient way of estimating the overlap statistics between collections and using this effectively combining this information in collection selection.

M3 - Patent

ER -