E97-1006 |
document classification based on
|
soft clustering
|
of words . Let cl , • •
|
E97-1006 |
finite mixture model based on
|
soft clustering
|
of words . We treat the problem
|
E14-1027 |
ideal for assessing the output of
|
soft clustering
|
algorithms . The third metric
|
E14-1027 |
whereas the BayesCat model returns a
|
soft clustering
|
of target nouns . In order to
|
E12-2018 |
clustering , another performs
|
soft clustering
|
. • CLUTO : the hierarchical
|
E12-1002 |
number of phrases is chosen for
|
soft clustering
|
. Both selections are done conservatively
|
E97-1006 |
( 2 ) Is it better to conduct
|
soft clustering
|
( FMM ) than to do hard clustering
|
D11-1118 |
. And exploring other uses of
|
soft clustering
|
algorithms -- perhaps as inputs
|
E03-1009 |
class . This is sometimes called
|
soft clustering
|
. Space does not permit an extensive
|
C02-1132 |
. An advantage of our EM-based
|
soft clustering
|
algorithm is that it can assign
|
C96-2205 |
above method , but they proposed a
|
soft clustering
|
scheme , in which membership
|
E09-1007 |
of clique-based clustering as a
|
soft clustering
|
method for other issues . <title>
|
D14-1057 |
models perform better than the
|
soft clustering
|
ones , achieving the second highest
|
C00-2121 |
, although more complex for "
|
soft clustering
|
" ( i.e. a word can be classified
|
C00-2121 |
. Of great importance is that
|
soft clustering
|
methods can also be applied to
|
E09-1007 |
clustering technique that amounts to a
|
soft clustering
|
method . Our experiments show
|
E14-1027 |
appropriate for evaluation of
|
soft clustering
|
output . We first create a K
|
D14-1057 |
makes our GermaNet SP model a
|
soft clustering
|
over nouns ( i.e. , a noun can
|
D13-1016 |
likely belongs to according to its
|
soft clustering
|
representation , such as c *
|
D14-1057 |
models , and suggest that simple
|
soft clustering
|
may be causing problems with
|