other,3-4-P05-1074,bq |
language as a pivot . We define a
<term>
|
paraphrase probability
|
</term>
that allows
<term>
paraphrases
</term>
|
#9719
We define aparaphrase probability that allows paraphrases extracted from a bilingual parallel corpus to be ranked using translation probabilities, and show how it can be refined to take contextual information into account. |
lr,11-4-P05-1074,bq |
paraphrases
</term>
extracted from a
<term>
|
bilingual parallel corpus
|
</term>
to be ranked using
<term>
translation
|
#9727
We define a paraphrase probability that allows paraphrases extracted from abilingual parallel corpus to be ranked using translation probabilities, and show how it can be refined to take contextual information into account. |
other,21-3-P05-1074,bq |
language
</term>
can be identified using a
<term>
|
phrase
|
</term>
in another language as a pivot .
|
#9708
Using alignment techniques from phrase-based statistical machine translation, we show how paraphrases in one language can be identified using aphrase in another language as a pivot. |
other,7-4-P05-1074,bq |
paraphrase probability
</term>
that allows
<term>
|
paraphrases
|
</term>
extracted from a
<term>
bilingual parallel
|
#9723
We define a paraphrase probability that allowsparaphrases extracted from a bilingual parallel corpus to be ranked using translation probabilities, and show how it can be refined to take contextual information into account. |
lr,18-2-P05-1074,bq |
</term>
, a much more commonly available
<term>
|
resource
|
</term>
. Using
<term>
alignment techniques
|
#9685
We show that this task can be done using bilingual parallel corpora, a much more commonly availableresource. |
other,24-5-P05-1074,bq |
<term>
paraphrases
</term>
extracted from
<term>
|
automatic alignments
|
</term>
. We present a
<term>
Czech-English
|
#9775
We evaluate our paraphrase extractio and ranking methods using a set of manual word alignments, and contrast the quality with paraphrases extracted fromautomatic alignments. |
tech,4-3-P05-1074,bq |
<term>
alignment techniques
</term>
from
<term>
|
phrase-based statistical machine translation
|
</term>
, we show how
<term>
paraphrases
</term>
|
#9691
Using alignment techniques fromphrase-based statistical machine translation, we show how paraphrases in one language can be identified using a phrase in another language as a pivot. |
other,11-1-P05-1074,bq |
corpora
</term>
to extract and generate
<term>
|
paraphrases
|
</term>
. We show that this task can be done
|
#9665
Previous work has used monolingual parallel corpora to extract and generateparaphrases. |
other,12-3-P05-1074,bq |
machine translation
</term>
, we show how
<term>
|
paraphrases
|
</term>
in one
<term>
language
</term>
can be
|
#9699
Using alignment techniques from phrase-based statistical machine translation, we show howparaphrases in one language can be identified using a phrase in another language as a pivot. |
other,15-3-P05-1074,bq |
how
<term>
paraphrases
</term>
in one
<term>
|
language
|
</term>
can be identified using a
<term>
phrase
|
#9702
Using alignment techniques from phrase-based statistical machine translation, we show how paraphrases in onelanguage can be identified using a phrase in another language as a pivot. |
tech,3-5-P05-1074,bq |
</term>
into account . We evaluate our
<term>
|
paraphrase extractio and ranking methods
|
</term>
using a set of
<term>
manual word alignments
|
#9754
We evaluate ourparaphrase extractio and ranking methods using a set of manual word alignments, and contrast the quality with paraphrases extracted from automatic alignments. |
other,30-4-P05-1074,bq |
show how it can be refined to take
<term>
|
contextual information
|
</term>
into account . We evaluate our
<term>
|
#9746
We define a paraphrase probability that allows paraphrases extracted from a bilingual parallel corpus to be ranked using translation probabilities, and show how it can be refined to takecontextual information into account. |
measure(ment),19-5-P05-1074,bq |
alignments
</term>
, and contrast the
<term>
|
quality
|
</term>
with
<term>
paraphrases
</term>
extracted
|
#9770
We evaluate our paraphrase extractio and ranking methods using a set of manual word alignments, and contrast thequality with paraphrases extracted from automatic alignments. |
lr,4-1-P05-1074,bq |
task
</term>
. Previous work has used
<term>
|
monolingual parallel corpora
|
</term>
to extract and generate
<term>
paraphrases
|
#9658
Previous work has usedmonolingual parallel corpora to extract and generate paraphrases. |
tech,1-3-P05-1074,bq |
available
<term>
resource
</term>
. Using
<term>
|
alignment techniques
|
</term>
from
<term>
phrase-based statistical
|
#9688
Usingalignment techniques from phrase-based statistical machine translation, we show how paraphrases in one language can be identified using a phrase in another language as a pivot. |
lr,9-2-P05-1074,bq |
show that this task can be done using
<term>
|
bilingual parallel corpora
|
</term>
, a much more commonly available
<term>
|
#9676
We show that this task can be done usingbilingual parallel corpora, a much more commonly available resource. |
other,18-4-P05-1074,bq |
parallel corpus
</term>
to be ranked using
<term>
|
translation probabilities
|
</term>
, and show how it can be refined
|
#9734
We define a paraphrase probability that allows paraphrases extracted from a bilingual parallel corpus to be ranked usingtranslation probabilities, and show how it can be refined to take contextual information into account. |
other,21-5-P05-1074,bq |
contrast the
<term>
quality
</term>
with
<term>
|
paraphrases
|
</term>
extracted from
<term>
automatic alignments
|
#9772
We evaluate our paraphrase extractio and ranking methods using a set of manual word alignments, and contrast the quality withparaphrases extracted from automatic alignments. |