H93-1105 |
continue to focus on classifier-based
|
sense resolution
|
methods . We hope to improve
|
H93-1061 |
constructed to use in studies of
|
sense resolution
|
in context ( semantic disambigua
|
H93-1051 |
frequency function words . With
|
sense resolution
|
, the salient tokens include
|
H93-1051 |
testing contexts is 44.5 words . The
|
sense resolution
|
task used the following six senses
|
H93-1061 |
of words that can be used for
|
sense resolution
|
. One solution would be to draw
|
H93-1051 |
network classifiers . For the
|
sense resolution
|
problem , each sense is represented
|
H93-1051 |
senses in WordNet . 1 Automatic
|
sense resolution
|
systems need to resolve highly
|
H93-1061 |
given us a tool for our studies of
|
sense resolution
|
in context . In the course of
|
H93-1103 |
such information will facilitate
|
sense resolution
|
. The value of such analyses
|
H93-1061 |
alternative methods of automatic
|
sense resolution
|
. The alternative strategy starts
|
H93-1051 |
does affect the difficulty of the
|
sense resolution
|
task , a greater factor of performance
|
H93-1061 |
promises to simplify the task of
|
sense resolution
|
. However , the morphology of
|
H93-1051 |
approach \ -LSB- 9 \ -RSB- casts
|
sense resolution
|
as a supervised learning paradigm
|
H93-1105 |
are currently studying automatic
|
sense resolution
|
procedures . In one approach
|
H93-1061 |
testing procedures for the automatic
|
sense resolution
|
in context . It should be pointed
|
H91-1077 |
. It will also be assumed that
|
sense resolution
|
for individual words can be accomplished
|
E97-1007 |
most of the techniques for word
|
sense resolution
|
have been presented as stand-alone
|
H93-1051 |
sense on corpus-based statistical
|
sense resolution
|
methods . To enable us to study
|
H93-1061 |
organization obviously facilitates
|
sense resolution
|
: if the topic is baseball ,
|
H91-1077 |
sense of a polysemous word . "
|
Sense resolution
|
" might be a better term , but
|