measure(ment),2-1-E06-1031,bq |
Most state-of-the-art
<term>
evaluation measures
</term>
for
<term>
machine translation
</term>
assign high
<term>
costs
</term>
to movements of
<term>
word
</term>
blocks .
|
#10325
Most state-of-the-artevaluation measures for machine translation assign high costs to movements of word blocks. |
tech,5-1-E06-1031,bq |
Most state-of-the-art
<term>
evaluation measures
</term>
for
<term>
machine translation
</term>
assign high
<term>
costs
</term>
to movements of
<term>
word
</term>
blocks .
|
#10328
Most state-of-the-art evaluation measures formachine translation assign high costs to movements of word blocks. |
other,9-1-E06-1031,bq |
Most state-of-the-art
<term>
evaluation measures
</term>
for
<term>
machine translation
</term>
assign high
<term>
costs
</term>
to movements of
<term>
word
</term>
blocks .
|
#10332
Most state-of-the-art evaluation measures for machine translation assign highcosts to movements of word blocks. |
other,13-1-E06-1031,bq |
Most state-of-the-art
<term>
evaluation measures
</term>
for
<term>
machine translation
</term>
assign high
<term>
costs
</term>
to movements of
<term>
word
</term>
blocks .
|
#10336
Most state-of-the-art evaluation measures for machine translation assign high costs to movements ofword blocks. |
other,13-2-E06-1031,bq |
In many cases though such movements still result in correct or almost correct
<term>
sentences
</term>
.
|
#10352
In many cases though such movements still result in correct or almost correctsentences. |
measure(ment),9-3-E06-1031,bq |
In this paper , we will present a new
<term>
evaluation measure
</term>
which explicitly models
<term>
block reordering
</term>
as an
<term>
edit operation
</term>
.
|
#10363
In this paper, we will present a newevaluation measure which explicitly models block reordering as an edit operation. |
tech,14-3-E06-1031,bq |
In this paper , we will present a new
<term>
evaluation measure
</term>
which explicitly models
<term>
block reordering
</term>
as an
<term>
edit operation
</term>
.
|
#10368
In this paper, we will present a new evaluation measure which explicitly modelsblock reordering as an edit operation. |
tech,18-3-E06-1031,bq |
In this paper , we will present a new
<term>
evaluation measure
</term>
which explicitly models
<term>
block reordering
</term>
as an
<term>
edit operation
</term>
.
|
#10372
In this paper, we will present a new evaluation measure which explicitly models block reordering as anedit operation. |
measure(ment),1-4-E06-1031,bq |
Our
<term>
measure
</term>
can be exactly calculated in
<term>
quadratic time
</term>
.
|
#10376
Ourmeasure can be exactly calculated in quadratic time. |
other,7-4-E06-1031,bq |
Our
<term>
measure
</term>
can be exactly calculated in
<term>
quadratic time
</term>
.
|
#10382
Our measure can be exactly calculated inquadratic time. |
measure(ment),7-5-E06-1031,bq |
Furthermore , we will show how some
<term>
evaluation measures
</term>
can be improved by the introduction of
<term>
word-dependent substitution costs
</term>
.
|
#10392
Furthermore, we will show how someevaluation measures can be improved by the introduction of word-dependent substitution costs. |
other,16-5-E06-1031,bq |
Furthermore , we will show how some
<term>
evaluation measures
</term>
can be improved by the introduction of
<term>
word-dependent substitution costs
</term>
.
|
#10401
Furthermore, we will show how some evaluation measures can be improved by the introduction ofword-dependent substitution costs. |
measure(ment),5-6-E06-1031,bq |
The correlation of the new
<term>
measure
</term>
with
<term>
human judgment
</term>
has been investigated systematically on two different
<term>
language pairs
</term>
.
|
#10410
The correlation of the newmeasure with human judgment has been investigated systematically on two different language pairs. |
other,7-6-E06-1031,bq |
The correlation of the new
<term>
measure
</term>
with
<term>
human judgment
</term>
has been investigated systematically on two different
<term>
language pairs
</term>
.
|
#10412
The correlation of the new measure withhuman judgment has been investigated systematically on two different language pairs. |
other,16-6-E06-1031,bq |
The correlation of the new
<term>
measure
</term>
with
<term>
human judgment
</term>
has been investigated systematically on two different
<term>
language pairs
</term>
.
|
#10421
The correlation of the new measure with human judgment has been investigated systematically on two differentlanguage pairs. |
other,12-7-E06-1031,bq |
The experimental results will show that it significantly outperforms state-of-the-art approaches in
<term>
sentence-level correlation
</term>
.
|
#10436
The experimental results will show that it significantly outperforms state-of-the-art approaches insentence-level correlation. |
other,4-8-E06-1031,bq |
Results from experiments with
<term>
word dependent substitution costs
</term>
will demonstrate an additional increase of correlation between
<term>
automatic evaluation measures
</term>
and
<term>
human judgment
</term>
.
|
#10443
Results from experiments withword dependent substitution costs will demonstrate an additional increase of correlation between automatic evaluation measures and human judgment. |
measure(ment),16-8-E06-1031,bq |
Results from experiments with
<term>
word dependent substitution costs
</term>
will demonstrate an additional increase of correlation between
<term>
automatic evaluation measures
</term>
and
<term>
human judgment
</term>
.
|
#10455
Results from experiments with word dependent substitution costs will demonstrate an additional increase of correlation betweenautomatic evaluation measures and human judgment. |
other,20-8-E06-1031,bq |
Results from experiments with
<term>
word dependent substitution costs
</term>
will demonstrate an additional increase of correlation between
<term>
automatic evaluation measures
</term>
and
<term>
human judgment
</term>
.
|
#10459
Results from experiments with word dependent substitution costs will demonstrate an additional increase of correlation between automatic evaluation measures andhuman judgment. |