tech,8-8-P05-1067,ak
shows that our system outperforms the
<term>
baseline system
</term>
based on the
<term>
IBM models
</term>
#9915
The result shows that our system outperforms thebaseline system based on the IBM models in both translation speed and quality.
measure(ment),12-7-P05-1067,ak
</term>
using the
<term>
NIST
</term>
and
<term>
Bleu automatic MT evaluation software
</term>
. The result shows that our system
#9901
We evaluate the outputs of our MT system using the NIST andBleu automatic MT evaluation software .
lr,12-3-P05-1067,ak
synchronous grammars
</term>
defined on
<term>
dependency trees
</term>
. We first introduce our approach
#9837
Synchronous dependency insertion grammars are a version of synchronous grammars defined ondependency trees .
lr,9-4-P05-1067,ak
introduce our approach to inducing such a
<term>
grammar
</term>
from
<term>
parallel corpora
</term>
#9849
We first introduce our approach to inducing such agrammar from parallel corpora.
model,5-5-P05-1067,ak
corpora
</term>
. Second , we describe the
<term>
graphical model
</term>
for the
<term>
machine translation
#9859
Second, we describe thegraphical model for the machine translation task, which can also be viewed as a stochastic tree-to-tree transducer.
model,13-8-P05-1067,ak
baseline system
</term>
based on the
<term>
IBM models
</term>
in both
<term>
translation speed and
#9920
The result shows that our system outperforms the baseline system based on theIBM models in both translation speed and quality.
other,9-5-P05-1067,ak
<term>
graphical model
</term>
for the
<term>
machine translation task
</term>
, which can also be viewed as a
<term>
#9863
Second, we describe the graphical model for themachine translation task , which can also be viewed as a stochastic tree-to-tree transducer.
model,9-6-P05-1067,ak
time decoding algorithm
</term>
for the
<term>
model
</term>
. We evaluate the outputs of our
<term>
#9887
We introduce a polynomial time decoding algorithm for themodel .
tech,6-7-P05-1067,ak
</term>
. We evaluate the outputs of our
<term>
MT system
</term>
using the
<term>
NIST
</term>
and
<term>
#9895
We evaluate the outputs of ourMT system using the NIST and Bleu automatic MT evaluation software.
measure(ment),10-7-P05-1067,ak
our
<term>
MT system
</term>
using the
<term>
NIST
</term>
and
<term>
Bleu automatic MT evaluation
#9899
We evaluate the outputs of our MT system using theNIST and Bleu automatic MT evaluation software.
lr,11-4-P05-1067,ak
inducing such a
<term>
grammar
</term>
from
<term>
parallel corpora
</term>
. Second , we describe the
<term>
graphical
#9851
We first introduce our approach to inducing such a grammar fromparallel corpora .
tech,3-6-P05-1067,ak
transducer
</term>
. We introduce a
<term>
polynomial time decoding algorithm
</term>
for the
<term>
model
</term>
. We evaluate
#9881
We introduce apolynomial time decoding algorithm for the model.
lr,15-2-P05-1067,ak
translation system
</term>
based on a
<term>
probabilistic synchronous dependency insertion grammar
</term>
.
<term>
Synchronous dependency insertion
#9819
In this paper, we present a syntax-based statistical machine translation system based on aprobabilistic synchronous dependency insertion grammar .
model,10-1-P05-1067,ak
translation ( MT )
</term>
aims at applying
<term>
statistical models
</term>
to
<term>
structured data
</term>
. In
#9798
Syntax-based statistical machine translation (MT) aims at applyingstatistical models to structured data.
tech,20-5-P05-1067,ak
</term>
, which can also be viewed as a
<term>
stochastic tree-to-tree transducer
</term>
. We introduce a
<term>
polynomial
#9874
Second, we describe the graphical model for the machine translation task, which can also be viewed as astochastic tree-to-tree transducer .
other,13-1-P05-1067,ak
applying
<term>
statistical models
</term>
to
<term>
structured data
</term>
. In this paper , we present a
<term>
#9801
Syntax-based statistical machine translation (MT) aims at applying statistical models tostructured data .
lr,0-3-P05-1067,ak
dependency insertion grammar
</term>
.
<term>
Synchronous dependency insertion grammars
</term>
are a version of
<term>
synchronous
#9825
In this paper, we present a syntax-based statistical machine translation system based on a probabilistic synchronous dependency insertion grammar.Synchronous dependency insertion grammars are a version of synchronous grammars defined on dependency trees.
lr,8-3-P05-1067,ak
insertion grammars
</term>
are a version of
<term>
synchronous grammars
</term>
defined on
<term>
dependency trees
</term>
#9833
Synchronous dependency insertion grammars are a version ofsynchronous grammars defined on dependency trees.
tech,0-1-P05-1067,ak
the state-of-the-art technologies .
<term>
Syntax-based statistical machine translation ( MT )
</term>
aims at applying
<term>
statistical
#9788
Experimental results show that our approach improves domain-specific word alignment in terms of both precision and recall, achieving a relative error rate reduction of 6.56% as compared with the state-of-the-art technologies.Syntax-based statistical machine translation ( MT ) aims at applying statistical models to structured data.
tech,7-2-P05-1067,ak
</term>
. In this paper , we present a
<term>
syntax-based statistical machine translation system
</term>
based on a
<term>
probabilistic synchronous
#9811
In this paper, we present asyntax-based statistical machine translation system based on a probabilistic synchronous dependency insertion grammar.