#9731In this paper, we first train two statistical word alignment models with thelarge-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these two models to improve the domain-specific word alignment.
lr,19-3-P05-1058,ak
out-of-domain corpus
</term>
and the
<term>
small-scale in-domain corpus
</term>
respectively , and then interpolate
#9736In this paper, we first train two statistical word alignment models with the large-scale out-of-domain corpus and thesmall-scale in-domain corpus respectively, and then interpolate these two models to improve the domain-specific word alignment.
lr,9-2-P05-1058,ak
alignment adaptation
</term>
is to use
<term>
out-of-domain corpus
</term>
to improve
<term>
in-domain word alignment
#9708The basic idea of alignment adaptation is to useout-of-domain corpus to improve in-domain word alignment results.
measure(ment),14-4-P05-1058,ak
word alignment
</term>
in terms of both
<term>
precision
</term>
and
<term>
recall
</term>
, achieving
#9768Experimental results show that our approach improves domain-specific word alignment in terms of bothprecision and recall, achieving a relative error rate reduction of 6.56% as compared with the state-of-the-art technologies.
measure(ment),16-4-P05-1058,ak
terms of both
<term>
precision
</term>
and
<term>
recall
</term>
, achieving a
<term>
relative error
#9770Experimental results show that our approach improves domain-specific word alignment in terms of both precision andrecall, achieving a relative error rate reduction of 6.56% as compared with the state-of-the-art technologies.
measure(ment),20-4-P05-1058,ak
and
<term>
recall
</term>
, achieving a
<term>
relative error rate reduction
</term>
of 6.56 % as compared with the state-of-the-art
#9774Experimental results show that our approach improves domain-specific word alignment in terms of both precision and recall, achieving arelative error rate reduction of 6.56% as compared with the state-of-the-art technologies.
model,29-3-P05-1058,ak
respectively , and then interpolate these two
<term>
models
</term>
to improve the
<term>
domain-specific
#9746In this paper, we first train two statistical word alignment models with the large-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these twomodels to improve the domain-specific word alignment.
model,8-3-P05-1058,ak
In this paper , we first train two
<term>
statistical word alignment models
</term>
with the
<term>
large-scale out-of-domain
#9725In this paper, we first train twostatistical word alignment models with the large-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these two models to improve the domain-specific word alignment.
other,13-2-P05-1058,ak
out-of-domain corpus
</term>
to improve
<term>
in-domain word alignment results
</term>
. In this paper , we first train
#9712The basic idea of alignment adaptation is to use out-of-domain corpus to improvein-domain word alignment results.
tech,33-3-P05-1058,ak
two
<term>
models
</term>
to improve the
<term>
domain-specific word alignment
</term>
. Experimental results show that
#9750In this paper, we first train two statistical word alignment models with the large-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these two models to improve thedomain-specific word alignment.
tech,4-1-P05-1058,ak
models
</term>
. This paper proposes an
<term>
alignment adaptation approach
</term>
to improve
<term>
domain-specific (
#9687This paper proposes analignment adaptation approach to improve domain-specific (in-domain) word alignment.
tech,4-2-P05-1058,ak
alignment
</term>
. The basic idea of
<term>
alignment adaptation
</term>
is to use
<term>
out-of-domain corpus
#9703The basic idea ofalignment adaptation is to use out-of-domain corpus to improve in-domain word alignment results.
tech,7-4-P05-1058,ak
results show that our approach improves
<term>
domain-specific word alignment
</term>
in terms of both
<term>
precision
</term>
#9761Experimental results show that our approach improvesdomain-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.
tech,9-1-P05-1058,ak
adaptation approach
</term>
to improve
<term>
domain-specific ( in-domain ) word alignment
</term>
. The basic idea of
<term>
alignment
#9692This paper proposes an alignment adaptation approach to improvedomain-specific ( in-domain ) word alignment.