lr,14-2-H92-1045,bq |
disambiguation systems
</term>
, one trained on
<term>
|
bilingual material
|
</term>
( the
<term>
Canadian Hansards
</term>
|
#19188
We have recently reported on two new word-sense disambiguation systems, one trained onbilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). |
lr,26-2-H92-1045,bq |
Hansards
</term>
) and the other trained on
<term>
|
monolingual material
|
</term>
(
<term>
Roget 's Thesaurus
</term>
and
|
#19200
We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained onmonolingual material (Roget's Thesaurus and Grolier's Encyclopedia). |
lr-prod,18-2-H92-1045,bq |
<term>
bilingual material
</term>
( the
<term>
|
Canadian Hansards
|
</term>
) and the other trained on
<term>
monolingual
|
#19192
We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (theCanadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). |
lr-prod,29-2-H92-1045,bq |
<term>
monolingual material
</term>
(
<term>
|
Roget 's Thesaurus
|
</term>
and
<term>
Grolier 's Encyclopedia
</term>
|
#19203
We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget 's Thesaurus and Grolier's Encyclopedia). |
lr-prod,33-2-H92-1045,bq |
<term>
Roget 's Thesaurus
</term>
and
<term>
|
Grolier 's Encyclopedia
|
</term>
) . As this work was nearing completion
|
#19207
We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus andGrolier 's Encyclopedia). |
other,10-6-H92-1045,bq |
be used as an additional source of
<term>
|
constraint
|
</term>
for improving the performance of
|
#19299
This result can be used as an additional source ofconstraint for improving the performance of the word-sense disambiguation algorithm. |
other,12-3-H92-1045,bq |
completion , we observed a very strong
<term>
|
discourse
|
</term>
effect . That is , if a
<term>
polysemous
|
#19224
As this work was nearing completion, we observed a very strongdiscourse effect. |
other,13-1-H92-1045,bq |
</term>
whose
<term>
meaning
</term>
or
<term>
|
sense
|
</term>
depends on the context of use . We
|
#19166
It is well-known that there are polysemous words like sentence whose meaning orsense depends on the context of use. |
other,16-5-H92-1045,bq |
and found that the tendency to share
<term>
|
sense
|
</term>
in the same
<term>
discourse
</term>
|
#19276
This paper describes an experiment which confirmed this hypothesis and found that the tendency to sharesense in the same discourse is extremely strong (98%). |
other,17-4-H92-1045,bq |
</term>
appears two or more times in a
<term>
|
well-written discourse
|
</term>
, it is extremely likely that they
|
#19244
That is, if a polysemous word such as sentence appears two or more times in awell-written discourse, it is extremely likely that they will all share the same sense. |
other,20-5-H92-1045,bq |
share
<term>
sense
</term>
in the same
<term>
|
discourse
|
</term>
is extremely strong ( 98 % ) . This
|
#19280
This paper describes an experiment which confirmed this hypothesis and found that the tendency to share sense in the samediscourse is extremely strong (98%). |
other,20-7-H92-1045,bq |
</term>
that did not make use of the
<term>
|
discourse constraint
|
</term>
. This paper describes an extension
|
#19330
In addition, it could also be used to help evaluate disambiguation algorithms that did not make use of thediscourse constraint. |
other,31-4-H92-1045,bq |
that they will all share the same
<term>
|
sense
|
</term>
. This paper describes an experiment
|
#19258
That is, if a polysemous word such as sentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the samesense. |
other,5-4-H92-1045,bq |
discourse
</term>
effect . That is , if a
<term>
|
polysemous word
|
</term>
such as
<term>
sentence
</term>
appears
|
#19232
That is, if apolysemous word such as sentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the same sense. |
other,6-1-H92-1045,bq |
</term>
. It is well-known that there are
<term>
|
polysemous words
|
</term>
like
<term>
sentence
</term>
whose
<term>
|
#19159
It is well-known that there arepolysemous words like sentence whose meaning or sense depends on the context of use. |
other,9-1-H92-1045,bq |
are
<term>
polysemous words
</term>
like
<term>
|
sentence
|
</term>
whose
<term>
meaning
</term>
or
<term>
|
#19162
It is well-known that there are polysemous words likesentence whose meaning or sense depends on the context of use. |
other,9-4-H92-1045,bq |
<term>
polysemous word
</term>
such as
<term>
|
sentence
|
</term>
appears two or more times in a
<term>
|
#19236
That is, if a polysemous word such assentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the same sense. |
tech,11-7-H92-1045,bq |
could also be used to help evaluate
<term>
|
disambiguation algorithms
|
</term>
that did not make use of the
<term>
|
#19321
In addition, it could also be used to help evaluatedisambiguation algorithms that did not make use of the discourse constraint. |
tech,17-6-H92-1045,bq |
for improving the performance of the
<term>
|
word-sense disambiguation algorithm
|
</term>
. In addition , it could also be
|
#19306
This result can be used as an additional source of constraint for improving the performance of theword-sense disambiguation algorithm. |
tech,7-2-H92-1045,bq |
have recently reported on two new
<term>
|
word-sense disambiguation systems
|
</term>
, one trained on
<term>
bilingual material
|
#19181
We have recently reported on two newword-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). |