The BNR model: foundations and performance of a Bayesian network-based retrieval model

Campos, Luis M. de; Fernández‐Luna, Juan M.; Huete, Juan F.

doi:10.1016/j.ijar.2003.07.011

Cited by 44 publications

(46 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This inference method has been widely and successfully applied in the Information Retrieval framework with the Bayesian Network Retrieval and the Context-based Influence Diagram models [2,3]. Moreover, this propagation has been proved to be exact, i.e.…”

Section: Categorizing Web Pages: Inferencementioning

confidence: 99%

“…For example, if X i has 20 parents (and this may be a common situation in our model), we need 2 20 (around one million) probability distributions, hence we cannot use a standard approach. Since computing and storing the conditional probabilities becomes prohibitive, we propose an approach that has been successfully used by the BNR model in the field of Information Retrieval [2] 5 which is based on the use of canonical models of multicausal interaction [11]. We shall therefore discuss the possible alternatives for each type of node:…”

Section: Assessment Of the Probability Distributionsmentioning

confidence: 99%

See 1 more Smart Citation

A Theoretical Framework for Web Categorization in Hierarchical Directories using Bayesian Networks

Campos

Fernández‐Luna

Huete

2006

Soft Computing in Web Information Retrieval

Self Cite

View full text Add to dashboard Cite

Section: Categorizing Web Pages: Inferencementioning

confidence: 99%

Section: Assessment Of the Probability Distributionsmentioning

confidence: 99%

A Theoretical Framework for Web Categorization in Hierarchical Directories using Bayesian Networks

Campos

Fernández‐Luna

Huete

2006

Soft Computing in Web Information Retrieval

Self Cite

View full text Add to dashboard Cite

“…configuration pa(X) of the corresponding parent sets P a(X), we use the canonical model proposed in [1], which supports a very efficient inference procedure. These probabilities are defined as follows:…”

Section: Figmentioning

confidence: 99%

“…To manage overlapping units we use the same criterion considered for the focused task. To rank the documents, we have considered three criteria to assign a relevance value to the entire document: the relevance value of a document is equal to: (1) the maximum relevance value of its units; (2) the relevance value of the "/article [1]" unit; (3) the sum of the relevance values of all its units. Some preliminary experimentation pointed out that the maximum criterion performed better, so we have used it in the official runs.…”

Section: Relevant In Context Taskmentioning

confidence: 99%

The Garnata Information Retrieval System at INEX’07

Campos

Fernández‐Luna

Huete

et al. 2008

Focused Access to XML Documents

Self Cite

View full text Add to dashboard Cite

Abstract. This paper exposes the results of our participation at INEX'07 in the AdHoc track and the comparison of these results with respect to the ones obtained last year. Three runs were submitted to each of the Focused, Relevant In Context and Best In Context tasks, all of them obtained with Garnata, our Information Retrieval System for structured documents. As in the past year, we use a model based on Influence Diagrams, the CID model. The result of our participation has been better than the last year and we have reached an acceptable position in the ranking for the three tasks. In the paper we describe the model, the system and we show the differences between our systems at INEX'06 and INEX'07, which make possible to get a better performance.

show abstract

“…Q = 1 and d j = 1 means respectively Q activated and d j activated. Recent researchers [4] [5], designed the Bayesian Network Retrieval Model, with a flexible topology that can take into account term relationships as well as document relationships. The meaning of document and query representations for all these models and relevant document retrieval is identical.…”

Section: Related Workmentioning

confidence: 99%

A Model for Information Retrieval Based on Possibilistic Networks

Brini¹,

Dubois²

2005

String Processing and Information Retrieval

View full text Add to dashboard Cite

Abstract. This paper proposes a model for Information Retrieval (IR) based on possibilistic directed networks. Relations documents-terms and query-terms are modeled through possibility and necessity measures rather than a probability measure. The relevance value for the document given the query is measured by two degrees: the necessity and the possibility. More precisely, the user's query triggers a propagation process to retrieve necessarily or at least possibly relevant documents. The possibility degree is convenient to filter documents out from the response (retrieved documents) and the necessity degree is useful for document relevance confirmation. Separating these notions may account for the imprecision pervading the retrieval process. Moreover, an improved weighting of terms in a query not present in the document is introduced. Experiments carried out on a sub-collection of CLEF, namely LeMonde 1994, a French newspapers collection, showed the effectiveness of the model.

show abstract

The BNR model: foundations and performance of a Bayesian network-based retrieval model

Cited by 44 publications

References 7 publications

A Theoretical Framework for Web Categorization in Hierarchical Directories using Bayesian Networks

A Theoretical Framework for Web Categorization in Hierarchical Directories using Bayesian Networks

The Garnata Information Retrieval System at INEX’07

A Model for Information Retrieval Based on Possibilistic Networks

Contact Info

Product

Resources

About