Meta-modelo funcional para recuperação de informação

by de Oliveira, Luciene Chagas

Abstract (Summary)
Modelling is one of the central tasks in the development of information retrieval systems. A usefultool for developing a new information retrieval model is a generic framework. This frameworks can beseen as formal meta-models that make possible to describe and to investigate formally the semanticsof the retrieval process and becomes possible to reason about features and properties of informationretrieval models (IR). With the growth and the differences between the IR strategies and modelsformal modelling comes becoming more and more important.In this dissertation, we propose a generic and formal framework for defining IR models namedFunctional Framework. This framework is a meta-model for IR models, defining a level of abstractionthat allows the representation, formulation and comparison of IR models. With this meta-model, IRmodels can be represented in a unique common language, which makes the study of characteristicsand properties of the models and the combination of these models easier. The framework also providesa formalism that permits the comparison of models without the need to carry out experiments.Moreover, we show examples of how to represent the three classic IR models and we designa model based on distance equivalent to the classic vector model using the framework functional.We also analyze the combination of multiple evidence, presenting two case studies of the use of theframework to combine multiple evidence in contexts bayesian belief networks and in the vector spacemodel. We show that the combination of multiple evidence in the bayesian belief network can becarried at in of several ways, being that each form corresponds to a similarity function in the vectormodel. The analysis of this correspondence is made through the functional framework. We show thatthe framework allows us to design new models and helps designers to modify these models to extendthem with new evidence sources. As application of the functional meta-model, we also present theideas of development of a meta-tool for experimental comparison between IR models.
This document abstract is also available in Portuguese.
Bibliographical Information:

Advisor:João Nunes de Souza; Ana Paula Laboissière Ambrósio; Sergio de Mello Schneider; Ilmério Reis da Silva

School:Universidade Federal de Uberlândia

School Location:Brazil

Source Type:Master's Thesis

Keywords:Functional framework Information retrieval models Formal models, Meta-model Combination of multiple evidence


Date of Publication:02/22/2006

© 2009 All Rights Reserved.