#29084We define for each category afinite mixture model based on soft clustering of words.
tech,11-2-P97-1006,ak
finite mixture model
</term>
based on
<term>
soft clustering
</term>
of
<term>
words
</term>
. We treat the
#29089We define for each category a finite mixture model based onsoft clustering of words.
other,14-2-P97-1006,ak
based on
<term>
soft clustering
</term>
of
<term>
words
</term>
. We treat the problem of classifying
#29092We define for each category a finite mixture model based on soft clustering ofwords.
tech,11-3-P97-1006,ak
classifying documents as that of conducting
<term>
statistical hypothesis testing
</term>
over
<term>
finite mixture models
</term>
#29105We treat the problem of classifying documents as that of conductingstatistical hypothesis testing over finite mixture models, and employ the EM algorithm to efficiently estimate parameters in a finite mixture model.
model,15-3-P97-1006,ak
statistical hypothesis testing
</term>
over
<term>
finite mixture models
</term>
, and employ the
<term>
EM algorithm
#29109We treat the problem of classifying documents as that of conducting statistical hypothesis testing overfinite mixture models, and employ the EM algorithm to efficiently estimate parameters in a finite mixture model.
tech,22-3-P97-1006,ak
mixture models
</term>
, and employ the
<term>
EM algorithm
</term>
to efficiently estimate
<term>
parameters
#29116We treat the problem of classifying documents as that of conducting statistical hypothesis testing over finite mixture models, and employ theEM algorithm to efficiently estimate parameters in a finite mixture model.
other,27-3-P97-1006,ak
algorithm
</term>
to efficiently estimate
<term>
parameters
</term>
in a
<term>
finite mixture model
</term>
#29121We treat the problem of classifying documents as that of conducting statistical hypothesis testing over finite mixture models, and employ the EM algorithm to efficiently estimateparameters in a finite mixture model.
model,30-3-P97-1006,ak
estimate
<term>
parameters
</term>
in a
<term>
finite mixture model
</term>
. Experimental results indicate that
#29124We treat the problem of classifying documents as that of conducting statistical hypothesis testing over finite mixture models, and employ the EM algorithm to efficiently estimate parameters in afinite mixture model.