#26120We have already proposed a model,TDMT ( Transfer-Driven Machine Translation ), that translates a sentence utilizing examples effectively and performs accurate structural disambiguation and target word selection.
tech,5-9-A94-1017,ak
extrapolation
</term>
. Thus , our model ,
<term>
TDMT
</term>
on
<term>
APs
</term>
, meets the vital
#26238Thus, our model,TDMT on APs, meets the vital requirements of spoken language translation.
tech,3-5-A94-1017,ak
requirement . In
<term>
TDMT
</term>
,
<term>
example-retrieval ( ER )
</term>
, i.e. , retrieving
<term>
examples
#26156In TDMT,example-retrieval ( ER ), i.e., retrieving examples most similar to an input expression, is the most dominant part of the total processing time.
tech,0-2-A94-1017,ak
spoken language translation
</term>
.
<term>
Spoken language translation
</term>
requires ( 1 ) an accurate
<term>
translation
#26095This paper proposes a model using associative processors (APs) for real-time spoken language translation.Spoken language translation requires (1) an accurate translation and (2) a real-time response.
other,16-6-A94-1017,ak
<term>
expressions
</term>
including a
<term>
frequent word
</term>
on
<term>
APs
</term>
. Experimental
#26199Our study has concluded that we only need to implement the ER for expressions including afrequent word on APs.
#26130We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates asentence utilizing examples effectively and performs accurate structural disambiguation and target word selection.
tech,9-2-A94-1017,ak
translation
</term>
requires ( 1 ) an accurate
<term>
translation
</term>
and ( 2 ) a real-time response .
#26104Spoken language translation requires (1) an accuratetranslation and (2) a real-time response.
tech,24-3-A94-1017,ak
</term>
effectively and performs accurate
<term>
structural disambiguation
</term>
and
<term>
target word selection
</term>
#26137We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizing examples effectively and performs accuratestructural disambiguation and target word selection.
other,12-8-A94-1017,ak
the
<term>
scalability
</term>
against
<term>
vocabulary size
</term>
by
<term>
extrapolation
</term>
. Thus
#26228Moreover, a study on communications between APs demonstrates the scalability againstvocabulary size by extrapolation.
other,16-5-A94-1017,ak
<term>
examples
</term>
most similar to an
<term>
input expression
</term>
, is the most dominant part of the
#26169In TDMT, example-retrieval (ER), i.e., retrieving examples most similar to aninput expression, is the most dominant part of the total processing time.
tech,27-3-A94-1017,ak
structural disambiguation
</term>
and
<term>
target word selection
</term>
. This paper will concentrate on
#26140We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizing examples effectively and performs accurate structural disambiguation andtarget word selection.
tech,7-8-A94-1017,ak
a study on communications between
<term>
APs
</term>
demonstrates the
<term>
scalability
#26223Moreover, a study on communications betweenAPs demonstrates the scalability against vocabulary size by extrapolation.
tech,15-8-A94-1017,ak
against
<term>
vocabulary size
</term>
by
<term>
extrapolation
</term>
. Thus , our model ,
<term>
TDMT
</term>
#26231Moreover, a study on communications between APs demonstrates the scalability against vocabulary size byextrapolation.
tech,12-1-A94-1017,ak
associative processors ( APs )
</term>
for
<term>
real-time spoken language translation
</term>
.
<term>
Spoken language translation
#26090This paper proposes a model using associative processors (APs) forreal-time spoken language translation.
other,13-6-A94-1017,ak
to implement the
<term>
ER
</term>
for
<term>
expressions
</term>
including a
<term>
frequent word
</term>
#26196Our study has concluded that we only need to implement the ER forexpressions including a frequent word on APs.
tech,1-5-A94-1017,ak
concentrate on the second requirement . In
<term>
TDMT
</term>
,
<term>
example-retrieval ( ER )
</term>
#26154InTDMT, example-retrieval (ER), i.e., retrieving examples most similar to an input expression, is the most dominant part of the total processing time.
tech,14-9-A94-1017,ak
</term>
, meets the vital requirements of
<term>
spoken language translation
</term>
.
<term>
Japanese texts
</term>
frequently
#26247Thus, our model, TDMT on APs, meets the vital requirements ofspoken language translation.
tech,7-9-A94-1017,ak
Thus , our model ,
<term>
TDMT
</term>
on
<term>
APs
</term>
, meets the vital requirements of
#26240Thus, our model, TDMT onAPs, meets the vital requirements of spoken language translation.
tech,19-6-A94-1017,ak
including a
<term>
frequent word
</term>
on
<term>
APs
</term>
. Experimental results show that
#26202Our study has concluded that we only need to implement the ER for expressions including a frequent word onAPs.
model,11-5-A94-1017,ak
example-retrieval ( ER )
</term>
, i.e. , retrieving
<term>
examples
</term>
most similar to an
<term>
input expression
#26164In TDMT, example-retrieval (ER), i.e., retrievingexamples most similar to an input expression, is the most dominant part of the total processing time.