measure(ment),16-2-N04-1022,bq |
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 measure translation performance . |
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 an MT 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, and syntactic structure from parse-trees of source and target language sentences. |
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 that MBR decoding can be used to tune statistical MT performance for specific loss functions. |