P11-1090 |
of multiple context vectors by
|
hierarchical smoothing
|
of distributions of different
|
W99-0612 |
Second , they support a natural
|
hierarchical smoothing
|
procedure for distributional
|
P10-1031 |
OntoUSP adopts a novel form of
|
hierarchical smoothing
|
by integrating it with the search
|
P10-1031 |
discovering ISA relations and performing
|
hierarchical smoothing
|
. 4.4 Discussion OntoUSP is a
|
P10-1031 |
relations , and using them for
|
hierarchical smoothing
|
. OntoUSP greatly outperformed
|
P10-1031 |
, we leverage the ontology for
|
hierarchical smoothing
|
and incorporate this smoothing
|
P11-1090 |
character language model . This
|
hierarchical smoothing
|
can be seen as an approximation
|
P99-1022 |
JAPAN ) . We propose methods of
|
hierarchical smoothing
|
of P ( wi Itopict ) in a topic-tree
|
P99-1022 |
evaluates new cluster generation ,
|
hierarchical smoothing
|
and adaptive topic-probability
|
P11-1090 |
set , including length penalty ,
|
hierarchical smoothing
|
parameters α , and the subset
|
P10-1031 |
constraints . Third , we introduce
|
hierarchical smoothing
|
into the model by replacing the
|
W02-2007 |
representations and support a natural
|
hierarchical smoothing
|
procedure for distributional
|