tech,2-1-N04-1022,bq |
<term>
EuroWordNet
</term>
. We present
<term>
|
Minimum Bayes-Risk ( MBR ) decoding
|
</term>
for
<term>
statistical machine translation
|
#6545
We presentMinimum Bayes-Risk ( MBR ) decoding for statistical machine translation. |
tech,9-1-N04-1022,bq |
Bayes-Risk ( MBR ) decoding
</term>
for
<term>
|
statistical machine translation
|
</term>
. This statistical approach aims
|
#6552
We present Minimum Bayes-Risk (MBR) decoding forstatistical machine translation. |
other,6-2-N04-1022,bq |
statistical approach aims to minimize
<term>
|
expected loss of translation errors
|
</term>
under
<term>
loss functions
</term>
that
|
#6562
This statistical approach aims to minimizeexpected loss of translation errors under loss functions that measure translation performance. |
measure(ment),16-2-N04-1022,bq |
<term>
loss functions
</term>
that measure
<term>
|
translation performance
|
</term>
. We describe a hierarchy of
<term>
|
#6572
This statistical approach aims to minimize expected loss of translation errors under loss functions that measuretranslation performance. |
other,12-3-N04-1022,bq |
that incorporate different levels of
<term>
|
linguistic information
|
</term>
from
<term>
word strings
</term>
,
<term>
|
#6587
We describe a hierarchy of loss functions that incorporate different levels oflinguistic information from word strings, word-to-word alignments from an MT system, and syntactic structure from parse-trees of source and target language sentences. |
other,18-3-N04-1022,bq |
</term>
from
<term>
word strings
</term>
,
<term>
|
word-to-word alignments
|
</term>
from an
<term>
MT system
</term>
, and
|
#6593
We describe a hierarchy of loss functions that incorporate different levels of linguistic information from word strings,word-to-word alignments from an MT system, and syntactic structure from parse-trees of source and target language sentences. |
tech,22-3-N04-1022,bq |
word-to-word alignments
</term>
from an
<term>
|
MT system
|
</term>
, and
<term>
syntactic structure
</term>
|
#6597
We describe a hierarchy of loss functions that incorporate different levels of linguistic information from word strings, word-to-word alignments from anMT system, and syntactic structure from parse-trees of source and target language sentences. |
other,26-3-N04-1022,bq |
from an
<term>
MT system
</term>
, and
<term>
|
syntactic structure
|
</term>
from
<term>
parse-trees
</term>
of
<term>
|
#6601
We describe a hierarchy of loss functions that incorporate different levels of linguistic information from word strings, word-to-word alignments from an MT system, andsyntactic structure from parse-trees of source and target language sentences. |
other,29-3-N04-1022,bq |
<term>
syntactic structure
</term>
from
<term>
|
parse-trees
|
</term>
of
<term>
source and target language
|
#6604
We describe a hierarchy of loss functions that incorporate different levels of linguistic information from word strings, word-to-word alignments from an MT system, and syntactic structure fromparse-trees of source and target language sentences. |
other,31-3-N04-1022,bq |
</term>
from
<term>
parse-trees
</term>
of
<term>
|
source and target language sentences
|
</term>
. We report the performance of the
|
#6606
We describe a hierarchy of loss functions that incorporate different levels of linguistic information from word strings, word-to-word alignments from an MT system, and syntactic structure from parse-trees ofsource and target language sentences. |
tech,6-4-N04-1022,bq |
. We report the performance of the
<term>
|
MBR decoders
|
</term>
on a
<term>
Chinese-to-English translation
|
#6618
We report the performance of theMBR decoders on a Chinese-to-English translation task. |
other,10-4-N04-1022,bq |
of the
<term>
MBR decoders
</term>
on a
<term>
|
Chinese-to-English translation task
|
</term>
. Our results show that
<term>
MBR
|
#6622
We report the performance of the MBR decoders on aChinese-to-English translation task. |
tech,4-5-N04-1022,bq |
task
</term>
. Our results show that
<term>
|
MBR decoding
|
</term>
can be used to tune
<term>
statistical
|
#6630
Our results show thatMBR decoding can be used to tune statistical MT performance for specific loss functions. |
tech,11-5-N04-1022,bq |
decoding
</term>
can be used to tune
<term>
|
statistical MT
|
</term>
performance for specific
<term>
loss
|
#6637
Our results show that MBR decoding can be used to tunestatistical MT performance for specific loss functions. |