PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

An Algebra for probabilistic XML retrieval
Benjamin Piwowarski and Patrick Gallinari
In: TDM 2004, 21 Jun 2004, Enschede, The Netherlands.

Abstract

In this article, we describe a new algebra for XML retrieval. We describe how to transform an XPath-like query in our algebra. This algebra contains a vague predicate, about, which defines a set of documents parts within an XML document that fullfill a query need like in classical Information Retrieval (IR). This predicate is evaluated in a probabilistic way: we give a probabilistic interpretation of our algebra. Answers to query needs expressed with vague content and vague structure constraints can then be evaluated.

Postscript - Requires a viewer, such as GhostView
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Information Retrieval & Textual Information Access
ID Code:197
Deposited By:Patrick Gallinari
Deposited On:06 June 2004