identification of paraphrases
</term>
from a
<term>
corpus of multiple English translations
</term>
of the same
<term>
source text
</term>
#1790We present an unsupervised learning algorithm for identification of paraphrases from acorpus of multiple English translations of the same source text.
other,12-3-P01-1008,ak
lexical paraphrases
</term>
as well as
<term>
syntactic paraphrases
</term>
. This paper presents a formal analysis
#1813Our approach yields phrasal and single word lexical paraphrases as well assyntactic paraphrases.
other,20-2-P01-1008,ak
English translations
</term>
of the same
<term>
source text
</term>
. Our approach yields
<term>
phrasal
#1798We present an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the samesource text.
other,22-1-P01-1008,ak
semi-automatic methods
</term>
to collect
<term>
paraphrases
</term>
. We present an
<term>
unsupervised
#1776While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collectparaphrases.
other,3-3-P01-1008,ak
source text
</term>
. Our approach yields
<term>
phrasal and single word lexical paraphrases
</term>
as well as
<term>
syntactic paraphrases
#1804Our approach yieldsphrasal and single word lexical paraphrases as well as syntactic paraphrases.
tech,1-1-P01-1008,ak
English grammar
</term>
are given . While
<term>
paraphrasing
</term>
is critical both for
<term>
interpretation
#1755Whileparaphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases.
tech,16-1-P01-1008,ak
language
</term>
, current systems use
<term>
manual or semi-automatic methods
</term>
to collect
<term>
paraphrases
</term>
#1770While paraphrasing is critical both for interpretation and generation of natural language, current systems usemanual or semi-automatic methods to collect paraphrases.
tech,3-2-P01-1008,ak
<term>
paraphrases
</term>
. We present an
<term>
unsupervised learning algorithm
</term>
for
<term>
identification of paraphrases
#1781We present anunsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text.
tech,6-1-P01-1008,ak
paraphrasing
</term>
is critical both for
<term>
interpretation and generation of natural language
</term>
, current systems use
<term>
manual
#1760While paraphrasing is critical both forinterpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases.
tech,7-2-P01-1008,ak
unsupervised learning algorithm
</term>
for
<term>
identification of paraphrases
</term>
from a
<term>
corpus of multiple English
#1785We present an unsupervised learning algorithm foridentification of paraphrases from a corpus of multiple English translations of the same source text.