#5367The paper presents aBayesian model for text summarization, which explicitly encodes and exploits information on how human judgments are distributed over the text.
tech,7-1-H05-1032,ak
presents a
<term>
Bayesian model
</term>
for
<term>
text summarization
</term>
, which explicitly encodes and exploits
#5370The paper presents a Bayesian model fortext summarization, which explicitly encodes and exploits information on how human judgments are distributed over the text.
other,18-1-H05-1032,ak
encodes and exploits information on how
<term>
human judgments
</term>
are distributed over the
<term>
text
#5381The paper presents a Bayesian model for text summarization, which explicitly encodes and exploits information on howhuman judgments are distributed over the text.
other,24-1-H05-1032,ak
judgments
</term>
are distributed over the
<term>
text
</term>
. Comparison is made against
<term>
#5387The paper presents a Bayesian model for text summarization, which explicitly encodes and exploits information on how human judgments are distributed over thetext.
tech,4-2-H05-1032,ak
</term>
. Comparison is made against
<term>
non Bayesian summarizers
</term>
, using
<term>
test data
</term>
from
#5393Comparison is made againstnon Bayesian summarizers, using test data from Japanese news texts.
other,9-2-H05-1032,ak
Bayesian summarizers
</term>
, using
<term>
test data
</term>
from
<term>
Japanese news texts
</term>
#5398Comparison is made against non Bayesian summarizers, usingtest data from Japanese news texts.
tech,5-3-H05-1032,ak
texts
</term>
. It is found that the
<term>
Bayesian approach
</term>
generally leverages performance of
#5410It is found that theBayesian approach generally leverages performance of a summarizer, at times giving it a significant lead over non-Bayesian models.
tech,12-3-H05-1032,ak
generally leverages performance of a
<term>
summarizer
</term>
, at times giving it a significant
#5417It is found that the Bayesian approach generally leverages performance of asummarizer, at times giving it a significant lead over non-Bayesian models.
tech,22-3-H05-1032,ak
giving it a significant lead over
<term>
non-Bayesian models
</term>
. We describe a new method for the
#5427It is found that the Bayesian approach generally leverages performance of a summarizer, at times giving it a significant lead overnon-Bayesian models.