tech,1-5-A94-1017,bq |
concentrate on the second requirement . In
<term>
|
TDMT
|
</term>
,
<term>
example-retrieval ( ER )
</term>
|
#20269
InTDMT, example-retrieval (ER), i.e., retrieving examples most similar to an input expression, is the most dominant part of the total processing time. |
tech,3-5-A94-1017,bq |
requirement . In
<term>
TDMT
</term>
,
<term>
|
example-retrieval ( ER )
|
</term>
, i.e. , retrieving examples most
|
#20271
In 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,5-9-A94-1017,bq |
extrapolation
</term>
. Thus , our model ,
<term>
|
TDMT on APs
|
</term>
, meets the vital requirements of
|
#20353
Thus, our model,TDMT on APs, meets the vital requirements of spoken language translation. |
tech,7-3-A94-1017,bq |
We have already proposed a model ,
<term>
|
TDMT ( Transfer-Driven Machine Translation )
|
</term>
, that translates a
<term>
sentence
|
#20235
We 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,19-6-A94-1017,bq |
including a frequent
<term>
word
</term>
on
<term>
|
APs
|
</term>
. Experimental results show that
|
#20317
Our study has concluded that we only need to implement the ER for expressions including a frequent word onAPs. |
other,14-9-A94-1017,bq |
</term>
, meets the vital requirements of
<term>
|
spoken language translation
|
</term>
.
<term>
Japanese texts
</term>
frequently
|
#20362
Thus, our model, TDMT on APs, meets the vital requirements ofspoken language translation. |
other,27-5-A94-1017,bq |
the most dominant part of the total
<term>
|
processing time
|
</term>
. Our study has concluded that we
|
#20295
In TDMT, example-retrieval (ER), i.e., retrieving examples most similar to an input expression, is the most dominant part of the totalprocessing time. |
other,12-1-A94-1017,bq |
associative processors ( APs )
</term>
for
<term>
|
real-time spoken language translation
|
</term>
.
<term>
Spoken language translation
|
#20205
This paper proposes a model using associative processors (APs) forreal-time spoken language translation. |
tech,27-3-A94-1017,bq |
structural disambiguation
</term>
and
<term>
|
target word selection
|
</term>
. This paper will concentrate on
|
#20255
We 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,15-8-A94-1017,bq |
against
<term>
vocabulary size
</term>
by
<term>
|
extrapolation
|
</term>
. Thus , our model ,
<term>
TDMT on
|
#20346
Moreover, a study on communications between APs demonstrates the scalability against vocabulary size byextrapolation. |
other,15-2-A94-1017,bq |
<term>
translation
</term>
and ( 2 ) a
<term>
|
real-time response
|
</term>
. We have already proposed a model
|
#20225
Spoken language translation requires (1) an accurate translation and (2) areal-time response. |
other,10-8-A94-1017,bq |
between
<term>
APs
</term>
demonstrates the
<term>
|
scalability
|
</term>
against
<term>
vocabulary size
</term>
|
#20341
Moreover, a study on communications between APs demonstrates thescalability against vocabulary size by extrapolation. |
other,9-2-A94-1017,bq |
translation
</term>
requires ( 1 ) an accurate
<term>
|
translation
|
</term>
and ( 2 ) a
<term>
real-time response
|
#20219
Spoken language translation requires (1) an accuratetranslation and (2) a real-time response. |
tech,24-3-A94-1017,bq |
effectively and performs accurate
<term>
|
structural disambiguation
|
</term>
and
<term>
target word selection
</term>
|
#20252
We 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,bq |
the
<term>
scalability
</term>
against
<term>
|
vocabulary size
|
</term>
by
<term>
extrapolation
</term>
. Thus
|
#20343
Moreover, a study on communications between APs demonstrates the scalability againstvocabulary size by extrapolation. |
tech,5-7-A94-1017,bq |
Experimental results show that the
<term>
|
ER
|
</term>
can be drastically speeded up . Moreover
|
#20324
Experimental results show that theER can be drastically speeded up. |
tech,7-8-A94-1017,bq |
a study on communications between
<term>
|
APs
|
</term>
demonstrates the
<term>
scalability
|
#20338
Moreover, a study on communications betweenAPs demonstrates the scalability against vocabulary size by extrapolation. |
tech,11-6-A94-1017,bq |
that we only need to implement the
<term>
|
ER
|
</term>
for
<term>
expressions
</term>
including
|
#20309
Our study has concluded that we only need to implement theER for expressions including a frequent word on APs. |
tech,6-1-A94-1017,bq |
This paper proposes a model using
<term>
|
associative processors ( APs )
|
</term>
for
<term>
real-time spoken language
|
#20199
This paper proposes a model usingassociative processors ( APs ) for real-time spoken language translation. |
other,13-6-A94-1017,bq |
to implement the
<term>
ER
</term>
for
<term>
|
expressions
|
</term>
including a frequent
<term>
word
</term>
|
#20311
Our study has concluded that we only need to implement the ER forexpressions including a frequent word on APs. |