#8871This method requires a source-language dependency parser,target language word segmentation and an unsupervised word alignment component.
lr,3-3-P05-1034,ak
alignment component
</term>
. We align a
<term>
parallel corpus
</term>
, project the
<term>
source dependency
#8885We align aparallel corpus, project the source dependency parse onto the target sentence, extract dependency treelet translation pairs, and train a tree-based ordering model.
tech,36-4-P05-1034,ak
linguistic generality available in a
<term>
parser
</term>
. In this paper , we present an
<term>
#8947We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in aparser.
other,4-2-P05-1034,ak
translation
</term>
. This method requires a
<term>
source-language
</term><term>
dependency parser
</term>
,
<term>
#8867This method requires asource-language dependency parser, target language word segmentation and an unsupervised word alignment component.
model,25-3-P05-1034,ak
translation pairs
</term>
, and train a
<term>
tree-based ordering model
</term>
. We describe an efficient
<term>
decoder
#8907We align a parallel corpus, project the source dependency parse onto the target sentence, extract dependency treelet translation pairs, and train atree-based ordering model.
other,14-2-P05-1034,ak
<term>
word segmentation
</term>
and an
<term>
unsupervised word alignment component
</term>
. We align a
<term>
parallel corpus
#8877This method requires a source-language dependency parser, target language word segmentation and anunsupervised word alignment component.
other,11-1-P05-1034,ak
machine translation
</term>
that combines
<term>
syntactic information
</term>
in the
<term>
source language
</term>
#8850We describe a novel approach to statistical machine translation that combinessyntactic information in the source language with recent advances in phrasal translation.
model,16-4-P05-1034,ak
</term>
in combination with conventional
<term>
SMT models
</term>
provides a promising approach that
#8927We describe an efficient decoder and show that using these tree-based models in combination with conventionalSMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.
tech,4-4-P05-1034,ak
model
</term>
. We describe an efficient
<term>
decoder
</term>
and show that using these
<term>
tree-based
#8915We describe an efficientdecoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.
other,17-3-P05-1034,ak
<term>
target sentence
</term>
, extract
<term>
dependency treelet translation pairs
</term>
, and train a
<term>
tree-based ordering
#8899We align a parallel corpus, project the source dependency parse onto the target sentence, extractdependency treelet translation pairs, and train a tree-based ordering model.
tech,21-1-P05-1034,ak
language
</term>
with recent advances in
<term>
phrasal translation
</term>
. This method requires a
<term>
source-language
#8860We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances inphrasal translation.
tech,10-2-P05-1034,ak
</term>
,
<term>
target language
</term><term>
word segmentation
</term>
and an
<term>
unsupervised word alignment
#8873This method requires a source-language dependency parser, target languageword segmentation and an unsupervised word alignment component.
tech,27-4-P05-1034,ak
approach that incorporates the power of
<term>
phrasal SMT
</term>
with the linguistic generality available
#8938We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power ofphrasal SMT with the linguistic generality available in a parser.
tech,5-2-P05-1034,ak
requires a
<term>
source-language
</term><term>
dependency parser
</term>
,
<term>
target language
</term><term>
#8868This method requires a source-languagedependency parser, target language word segmentation and an unsupervised word alignment component.
other,15-1-P05-1034,ak
syntactic information
</term>
in the
<term>
source language
</term>
with recent advances in
<term>
phrasal
#8854We describe a novel approach to statistical machine translation that combines syntactic information in thesource language with recent advances in phrasal translation.
other,13-3-P05-1034,ak
source dependency parse
</term>
onto the
<term>
target sentence
</term>
, extract
<term>
dependency treelet
#8895We align a parallel corpus, project the source dependency parse onto thetarget sentence, extract dependency treelet translation pairs, and train a tree-based ordering model.
other,8-3-P05-1034,ak
parallel corpus
</term>
, project the
<term>
source dependency parse
</term>
onto the
<term>
target sentence
</term>
#8890We align a parallel corpus, project thesource dependency parse onto the target sentence, extract dependency treelet translation pairs, and train a tree-based ordering model.
model,10-4-P05-1034,ak
decoder
</term>
and show that using these
<term>
tree-based models
</term>
in combination with conventional
<term>
#8921We describe an efficient decoder and show that using thesetree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.
tech,6-1-P05-1034,ak
</term>
. We describe a novel approach to
<term>
statistical machine translation
</term>
that combines
<term>
syntactic information
#8845We describe a novel approach tostatistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation.