other,3-1-C04-1106,bq |
</term>
significantly . The reality of
<term>
|
analogies between words
|
</term>
is refuted by noone ( e.g. , I walked
|
#5845
The reality ofanalogies between words is refuted by noone (e.g., I walked is to to walk as I laughed is to to laugh, noted I walked : to walk :: I laughed : to laugh). |
other,1-2-C04-1106,bq |
walk : : I laughed : to laugh ) . But
<term>
|
computational linguists
|
</term>
seem to be quite dubious about
<term>
|
#5885
Butcomputational linguists seem to be quite dubious about analogies between sentences: they would not be enough numerous to be of any use. |
other,9-2-C04-1106,bq |
</term>
seem to be quite dubious about
<term>
|
analogies between sentences
|
</term>
: they would not be enough numerous
|
#5893
But computational linguists seem to be quite dubious aboutanalogies between sentences: they would not be enough numerous to be of any use. |
lr,6-3-C04-1106,bq |
report experiments conducted on a
<term>
|
multilingual corpus
|
</term>
to estimate the number of
<term>
analogies
|
#5915
We report experiments conducted on amultilingual corpus to estimate the number of analogies among the sentences that it contains. |
other,13-3-C04-1106,bq |
corpus
</term>
to estimate the number of
<term>
|
analogies
|
</term>
among the
<term>
sentences
</term>
that
|
#5922
We report experiments conducted on a multilingual corpus to estimate the number ofanalogies among the sentences that it contains. |
other,16-3-C04-1106,bq |
of
<term>
analogies
</term>
among the
<term>
|
sentences
|
</term>
that it contains . We give two estimates
|
#5925
We report experiments conducted on a multilingual corpus to estimate the number of analogies among thesentences that it contains. |
other,2-5-C04-1106,bq |
lower one and a higher one . As an
<term>
|
analogy
|
</term>
must be valid on the level of
<term>
|
#5945
As ananalogy must be valid on the level of form as well as on the level of meaning, we relied on the idea that translation should preserve meaning to test for similar meanings. |
other,10-5-C04-1106,bq |
</term>
must be valid on the level of
<term>
|
form
|
</term>
as well as on the level of
<term>
meaning
|
#5953
As an analogy must be valid on the level ofform as well as on the level of meaning, we relied on the idea that translation should preserve meaning to test for similar meanings. |
other,26-5-C04-1106,bq |
</term>
, we relied on the idea that
<term>
|
translation
|
</term>
should preserve
<term>
meaning
</term>
|
#5969
As an analogy must be valid on the level of form as well as on the level of meaning, we relied on the idea thattranslation should preserve meaning to test for similar meanings. |
other,34-5-C04-1106,bq |
<term>
meaning
</term>
to test for similar
<term>
|
meanings
|
</term>
. In this paper , we present a
<term>
|
#5977
As an analogy must be valid on the level of form as well as on the level of meaning, we relied on the idea that translation should preserve meaning to test for similarmeanings. |