The Paice model[3]​ is a general extension

for the MMM model. Compared to the MMM model that considers

only the minimum and maximum weights for the indexed terms,

The Paice model incorporates all the weights of the terms

when calculating similarity:.

where r is a constant coefficient and w is organized

in ascending order for queries and, and in descending order for

queries o. When n = 2 the Paice model shows the same

behavior than the MMM model.

The experiments of Lee and Fox[2]​ have shown that

setting r to 1.0 for queries and, and 0.7 for

queries o provide good effectiveness in the

recovery. The computational cost for this model is higher

than for the MMM model. This is because the MMM model only needs

the determination of the minimum or maximum of a set of

term weights whenever a clause and or or is

considered, which can be done in O(n). The Paice model

requires that the weights of the terms be arranged in order

ascending or descending, depending on whether it is considered a

and clause or an or clause. This requires at least

Lee and Fox[2]​ compared the Standard Boolean model with

the MMM and Paice models with three test collections:

CISI, CACM, and INSPEC. These are the reported results

for the improvement of the average of the average precision:.

These are very nice improvements over the Standard model. MMM it's very close

to the Paice and noma-P results, indicating that it may be

a very good technique, and it is the most efficient of the three.

Recently Kang et al.[4]​ have invented a fuzzy retrieval system indexed by concept identification.

If we look at documents on a pure Tf-idf approach, even eliminating stop words, there will be words more relevant to the topic of the document than others and they will have the same weight because they have the same frequency of terms. If we take into account the user's intention regarding a query, we can improve the weight of the terms of a document. Each term can be identified as a concept in a certain lexical chain that translates the importance of that concept for that document.

They reported improvements over Paice and P-norm on average precision and recovery of the top 5 retrieved documents.

Zadrozny[5]​ reviewed the fuzzy information retrieval model. Additionally extended the fuzzy extended Boolean model:

The proposed model makes it possible to capture imprecision and uncertainty concerning the representation and retrieval of textual information.

Betrabet, M. Koushik, W. Lee (1992), Information Retrieval: Algorithms and Data structures; Extended Boolean model, Prentice-Hall,

Inc., archived from the original on September 28, 2013.

The Paice model[3]​ is a general extension

for the MMM model. Compared to the MMM model that considers

only the minimum and maximum weights for the indexed terms,

The Paice model incorporates all the weights of the terms

when calculating similarity:.

where r is a constant coefficient and w is organized

in ascending order for queries and, and in descending order for

queries o. When n = 2 the Paice model shows the same

behavior than the MMM model.

The experiments of Lee and Fox[2]​ have shown that

setting r to 1.0 for queries and, and 0.7 for

queries o provide good effectiveness in the

recovery. The computational cost for this model is higher

than for the MMM model. This is because the MMM model only needs

the determination of the minimum or maximum of a set of

term weights whenever a clause and or or is

considered, which can be done in O(n). The Paice model

requires that the weights of the terms be arranged in order

ascending or descending, depending on whether it is considered a

and clause or an or clause. This requires at least

Lee and Fox[2]​ compared the Standard Boolean model with

the MMM and Paice models with three test collections:

CISI, CACM, and INSPEC. These are the reported results

for the improvement of the average of the average precision:.

These are very nice improvements over the Standard model. MMM it's very close

to the Paice and noma-P results, indicating that it may be

a very good technique, and it is the most efficient of the three.

Recently Kang et al.[4]​ have invented a fuzzy retrieval system indexed by concept identification.

If we look at documents on a pure Tf-idf approach, even eliminating stop words, there will be words more relevant to the topic of the document than others and they will have the same weight because they have the same frequency of terms. If we take into account the user's intention regarding a query, we can improve the weight of the terms of a document. Each term can be identified as a concept in a certain lexical chain that translates the importance of that concept for that document.

They reported improvements over Paice and P-norm on average precision and recovery of the top 5 retrieved documents.

Zadrozny[5]​ reviewed the fuzzy information retrieval model. Additionally extended the fuzzy extended Boolean model:

The proposed model makes it possible to capture imprecision and uncertainty concerning the representation and retrieval of textual information.

Betrabet, M. Koushik, W. Lee (1992), Information Retrieval: Algorithms and Data structures; Extended Boolean model, Prentice-Hall,

Inc., archived from the original on September 28, 2013.