N04-4002 |
. In this dataset , however ,
|
MMR-based feature selection
|
does not produce improvements
|
N04-4002 |
text categorization . Besides ,
|
MMR-based feature selection
|
method sometimes produces improvements
|
N04-4002 |
becomes more critical . <title>
|
MMR-based feature selection
|
for text categorization </title>
|
N04-4002 |
Feature Selection We propose a
|
MMR-based feature selection
|
which selects each feature according
|
N04-4002 |
for text categorization . Our
|
MMR-based feature selection
|
method strives to reduce redundancy
|
N04-4002 |
Reuters after term selection using
|
MMR-based feature selection
|
( number of features is 25 )
|
N04-4002 |
terms ) . In this data set , again
|
MMR-based feature selection
|
has best performance and significant
|
N04-4002 |
WebKB are highly consistent .
|
MMR-based feature selection
|
is consistently more effective
|
N04-4002 |
feature selection method . Using
|
MMR-based feature selection
|
the best accuracy is 82.47 %
|
N04-4002 |
using IG , and then we applied
|
MMR-based feature selection
|
and greedy feature selection
|
N04-4002 |
method and SVM using all features .
|
MMR-based feature selection
|
and greedy feature selection
|
N04-4002 |
computational cost , we can use
|
MMR-based feature selection
|
method on the reduced feature
|
N04-4002 |
In this paper , we proposed a
|
MMR-based feature selection
|
method which strives to reduce
|
N04-4002 |
Sim1 or a different metric . 3
|
MMR-based Feature Selection
|
We propose a MMR-based feature
|
N04-4002 |
support 10-fold cross validation .
|
MMR-based feature selection
|
method needs to tune for A .
|
N04-4002 |
accuracy . A disadvantage in using
|
MMR-based feature selection
|
is that the computational cost
|
N04-4002 |
in section 3 , we describe the
|
MMR-based feature selection
|
. Section 4 presents the in-depth
|
N04-4002 |
. Empirical results show that
|
MMR-based feature selection
|
is more effective than Koller
|
N04-4002 |
novelty of information . We define
|
MMR-based feature selection
|
as follows : MMR FS _ Arg max
|
N04-4002 |
experiment results , we can verify that
|
MMR-based feature selection
|
is more effective than Koller
|