#5165In this paper, we use the information redundancy in multilingual input to correcterrors in machine translation and thus improve the quality of multilingual summaries.
tech,5-2-H05-1005,ak
summaries . We consider the case of
<term>
multi-document summarization
</term>
, where the input documents are in
#5183We consider the case ofmulti-document summarization, where the input documents are in Arabic, and the output summary is in English.
other,13-3-H05-1005,ak
summary appears in many different
<term>
lexical-syntactic forms
</term>
in the input documents . Further
#5215Typically, information that makes it to a summary appears in many differentlexical-syntactic forms in the input documents.
tech,6-4-H05-1005,ak
documents . Further , the use of multiple
<term>
machine translation systems
</term>
provides yet more
<term>
redundancy
#5228Further, the use of multiplemachine translation systems provides yet more redundancy, yielding different ways to realize that information in English.
other,12-4-H05-1005,ak
translation systems
</term>
provides yet more
<term>
redundancy
</term>
, yielding different ways to realize
#5234Further, the use of multiple machine translation systems provides yet moreredundancy, yielding different ways to realize that information in English.
other,3-5-H05-1005,ak
information in English . We demonstrate how
<term>
errors
</term>
in the
<term>
machine translations
</term>
#5249We demonstrate howerrors in the machine translations of the input Arabic documents can be corrected by identifying and generating from such redundancy, focusing on noun phrases.
other,6-5-H05-1005,ak
demonstrate how
<term>
errors
</term>
in the
<term>
machine translations
</term>
of the input Arabic documents can
#5252We demonstrate how errors in themachine translations of the input Arabic documents can be corrected by identifying and generating from such redundancy, focusing on noun phrases.
other,22-5-H05-1005,ak
identifying and generating from such
<term>
redundancy
</term>
, focusing on
<term>
noun phrases
</term>
#5268We demonstrate how errors in the machine translations of the input Arabic documents can be corrected by identifying and generating from suchredundancy, focusing on noun phrases.
other,26-5-H05-1005,ak
<term>
redundancy
</term>
, focusing on
<term>
noun phrases
</term>
. This paper presents a
<term>
maximum
#5272We demonstrate how errors in the machine translations of the input Arabic documents can be corrected by identifying and generating from such redundancy, focusing onnoun phrases.