tech,9-1-E06-1018,bq |
a novel solution to automatic and
<term>
|
unsupervised word sense induction ( WSI )
|
</term>
is introduced . It represents an
|
#10096
In this paper a novel solution to automatic andunsupervised word sense induction ( WSI ) is introduced. |
other,6-2-E06-1018,bq |
represents an instantiation of the
<term>
|
one sense per collocation observation
|
</term>
( Gale et al. , 1992 ) . Like most
|
#10112
It represents an instantiation of theone sense per collocation observation (Gale et al., 1992). |
tech,7-4-E06-1018,bq |
approach differs from other approaches to
<term>
|
WSI
|
</term>
in that it enhances the effect of
|
#10143
This approach differs from other approaches toWSI in that it enhances the effect of the one sense per collocation observation by using triplets of words instead of pairs. |
other,16-4-E06-1018,bq |
that it enhances the effect of the
<term>
|
one sense per collocation observation
|
</term>
by using triplets of
<term>
words
</term>
|
#10152
This approach differs from other approaches to WSI in that it enhances the effect of theone sense per collocation observation by using triplets of words instead of pairs. |
other,25-4-E06-1018,bq |
observation
</term>
by using triplets of
<term>
|
words
|
</term>
instead of pairs . The combination
|
#10161
This approach differs from other approaches to WSI in that it enhances the effect of the one sense per collocation observation by using triplets ofwords instead of pairs. |
tech,4-5-E06-1018,bq |
of pairs . The combination with a
<term>
|
two-step clustering process
|
</term>
using
<term>
sentence co-occurrences
|
#10170
The combination with atwo-step clustering process using sentence co-occurrences as features allows for accurate results. |
other,8-5-E06-1018,bq |
two-step clustering process
</term>
using
<term>
|
sentence co-occurrences
|
</term>
as
<term>
features
</term>
allows for
|
#10174
The combination with a two-step clustering process usingsentence co-occurrences as features allows for accurate results. |
other,11-5-E06-1018,bq |
<term>
sentence co-occurrences
</term>
as
<term>
|
features
|
</term>
allows for accurate results . Additionally
|
#10177
The combination with a two-step clustering process using sentence co-occurrences asfeatures allows for accurate results. |
tech,8-6-E06-1018,bq |
a novel and likewise automatic and
<term>
|
unsupervised evaluation method
|
</term>
inspired by Schutze 's ( 1992 ) idea
|
#10191
Additionally, a novel and likewise automatic andunsupervised evaluation method inspired by Schutze's (1992) idea of evaluation of word sense disambiguation algorithms is employed. |
other,20-6-E06-1018,bq |
inspired by Schutze 's ( 1992 ) idea of
<term>
|
evaluation
|
</term>
of
<term>
word sense disambiguation
|
#10203
Additionally, a novel and likewise automatic and unsupervised evaluation method inspired by Schutze's (1992) idea ofevaluation of word sense disambiguation algorithms is employed. |
tech,22-6-E06-1018,bq |
) idea of
<term>
evaluation
</term>
of
<term>
|
word sense disambiguation algorithms
|
</term>
is employed . Offering advantages
|
#10205
Additionally, a novel and likewise automatic and unsupervised evaluation method inspired by Schutze's (1992) idea of evaluation ofword sense disambiguation algorithms is employed. |
lr,10-7-E06-1018,bq |
and independency of a given biased
<term>
|
gold standard
|
</term>
it also enables
<term>
automatic parameter
|
#10222
Offering advantages like reproducability and independency of a given biasedgold standard it also enables automatic parameter optimization of the WSI algorithm. |
tech,15-7-E06-1018,bq |
gold standard
</term>
it also enables
<term>
|
automatic parameter optimization
|
</term>
of the
<term>
WSI algorithm
</term>
.
|
#10227
Offering advantages like reproducability and independency of a given biased gold standard it also enablesautomatic parameter optimization of the WSI algorithm. |
tech,20-7-E06-1018,bq |
parameter optimization
</term>
of the
<term>
|
WSI algorithm
|
</term>
. We present results on
<term>
addressee
|
#10232
Offering advantages like reproducability and independency of a given biased gold standard it also enables automatic parameter optimization of theWSI algorithm. |