#3085In order to boost thetranslation quality of EBMT based on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus.
tech,8-1-N03-2006,ak
<term>
translation quality
</term>
of
<term>
EBMT
</term>
based on a
<term>
small-sized bilingual
#3088In order to boost the translation quality ofEBMT based on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus.
lr,12-1-N03-2006,ak
</term>
of
<term>
EBMT
</term>
based on a
<term>
small-sized bilingual corpus
</term>
, we use an
<term>
out-of-domain bilingual
#3092In order to boost the translation quality of EBMT based on asmall-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus.
lr,19-1-N03-2006,ak
bilingual corpus
</term>
, we use an
<term>
out-of-domain bilingual corpus
</term>
and , in addition , the
<term>
language
#3099In order to boost the translation quality of EBMT based on a small-sized bilingual corpus, we use anout-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus.
model,28-1-N03-2006,ak
corpus
</term>
and , in addition , the
<term>
language model
</term>
of an
<term>
in-domain monolingual
#3108In order to boost the translation quality of EBMT based on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, thelanguage model of an in-domain monolingual corpus.
lr,32-1-N03-2006,ak
the
<term>
language model
</term>
of an
<term>
in-domain monolingual corpus
</term>
. We conducted experiments with an
#3112In order to boost the translation quality of EBMT based on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of anin-domain monolingual corpus.
tech,5-2-N03-2006,ak
. We conducted experiments with an
<term>
EBMT system
</term>
. The two
<term>
evaluation measures
#3121We conducted experiments with anEBMT system.
measure(ment),2-3-N03-2006,ak
an
<term>
EBMT system
</term>
. The two
<term>
evaluation measures
</term>
of the
<term>
BLEU score
</term>
and
#3126The twoevaluation measures of the BLEU score and the NIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using the language model.
measure(ment),6-3-N03-2006,ak
<term>
evaluation measures
</term>
of the
<term>
BLEU score
</term>
and the
<term>
NIST score
</term>
demonstrated
#3130The two evaluation measures of theBLEU score and the NIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using the language model.
measure(ment),10-3-N03-2006,ak
the
<term>
BLEU score
</term>
and the
<term>
NIST score
</term>
demonstrated the effect of using
#3134The two evaluation measures of the BLEU score and theNIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using the language model.
lr,18-3-N03-2006,ak
demonstrated the effect of using an
<term>
out-of-domain bilingual corpus
</term>
and the possibility of using the
<term>
#3142The two evaluation measures of the BLEU score and the NIST score demonstrated the effect of using anout-of-domain bilingual corpus and the possibility of using the language model.
model,27-3-N03-2006,ak
</term>
and the possibility of using the
<term>
language model
</term>
. We describe a simple
<term>
unsupervised
#3151The two evaluation measures of the BLEU score and the NIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using thelanguage model.