Negative filter
monolingual, parallel, corpora 15
(480.2 per million)
lr,9-2-P05-1074,ak
show that this task can be done using
<term>
bilingual parallel corpora
</term>
, a much more commonly available
#10165We show that this task can be done usingbilingual parallel corpora, a much more commonly available resource.
lr,12-5-P05-1074,ak
ranking methods
</term>
using a set of
<term>
manual word alignments
</term>
, and contrast the quality with
<term>
#10252We evaluate our paraphrase extraction and ranking methods using a set ofmanual word alignments, and contrast the quality with paraphrases extracted from automatic alignments.
measure(ment),18-4-P05-1074,ak
parallel corpus
</term>
to be ranked using
<term>
translation probabilities
</term>
, and show how it can be refined
#10223We 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.
tech,4-3-P05-1074,ak
<term>
alignment techniques
</term>
from
<term>
phrase-based statistical machine translation
</term>
, we show how
<term>
paraphrases
</term>
#10180Using 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.
lr,24-5-P05-1074,ak
<term>
paraphrases
</term>
extracted from
<term>
automatic alignments
</term>
. This paper describes a novel system
#10264We evaluate our paraphrase extraction and ranking methods using a set of manual word alignments, and contrast the quality with paraphrases extracted fromautomatic alignments.
other,11-1-P05-1074,ak
corpora
</term>
to extract and generate
<term>
paraphrases
</term>
. We show that this task can be done
#10154Previous work has used monolingual parallel corpora to extract and generateparaphrases.
other,7-4-P05-1074,ak
paraphrase probability
</term>
that allows
<term>
paraphrases
</term>
extracted from a
<term>
bilingual parallel
#10212We 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.
other,21-5-P05-1074,ak
</term>
, and contrast the quality with
<term>
paraphrases
</term>
extracted from
<term>
automatic alignments
#10261We evaluate our paraphrase extraction and ranking methods using a set of manual word alignments, and contrast the quality withparaphrases extracted from automatic alignments.
tech,1-3-P05-1074,ak
commonly available resource . Using
<term>
alignment techniques
</term>
from
<term>
phrase-based statistical
#10177Usingalignment 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.
other,21-3-P05-1074,ak
language can be identified using a
<term>
phrase
</term>
in another language as a pivot .
#10197Using 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,12-3-P05-1074,ak
machine translation
</term>
, we show how
<term>
paraphrases
</term>
in one language can be identified
#10188Using 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,30-4-P05-1074,ak
show how it can be refined to take
<term>
contextual information
</term>
into account . We evaluate our
<term>
#10235We 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),3-4-P05-1074,ak
language as a pivot . We define a
<term>
paraphrase probability
</term>
that allows
<term>
paraphrases
</term>
#10208We 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,ak
paraphrases
</term>
extracted from a
<term>
bilingual parallel corpus
</term>
to be ranked using
<term>
translation
#10216We 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.
tech,3-5-P05-1074,ak
</term>
into account . We evaluate our
<term>
paraphrase extraction and ranking methods
</term>
using a set of
<term>
manual word alignments
#10243We evaluate ourparaphrase extraction and ranking methods using a set of manual word alignments, and contrast the quality with paraphrases extracted from automatic alignments.