From uncertain inference to probability of relevance for advanced IR applications

by Nottelmann, Henrik; Fuhr, Norbert

Abstract (Summary)
Uncertain inference is a probabilistic generalisation of the logical view on databases, ranking documents according to their probabilities that they logically imply the query. For tasks other than ad-hoc retrieval, estimates of the actual probability of relevance are required. In this paper, we investigate mapping functions between these two types of probability. For this purpose, we consider linear and logistic functions. The former have been proposed before, whereas we give a new theoretic justification for the latter. In a series of upper-bound experiments, we compare the goodness of fit of the two models. A second series of experiments investigates the effect on the resulting retrieval quality in the fusion step of distributed retrieval. These experiments show that good estimates of the actual probability of relevance can be achieved, and the logistic model outperforms the linear one. However, retrieval quality for distributed retrieval (only merging, without resource selection) is only slightly improved by using the logistic function


Advances in information retrieval : proceedings / 25th European Conference on IR Research, ECIR 2003, Pisa, Italy, April 14 - 16, 2003. Fabrizio Sebastiani (ed.). - Berlin : Springer, 2003. - S. 235-250

Bibliographical Information:


School:Universität Duisburg-Essen, Standort Essen

School Location:Germany

Source Type:Master's Thesis

Keywords:informatik datenverarbeitung universitaet duisburg essen


Date of Publication:07/16/2004

© 2009 All Rights Reserved.