generation system
</term>
designed to create
<term>
cohesive text
</term>
through the use of
<term>
lexical substitutions
#15473This report describes Paul, a computer text generation system designed to createcohesive text through the use of lexical substitutions.
tech,6-1-P84-1078,ak
report describes
<term>
Paul
</term>
, a
<term>
computer text generation system
</term>
designed to create
<term>
cohesive
#15466This report describes Paul, acomputer text generation system designed to create cohesive text through the use of lexical substitutions.
other,16-2-P84-1078,ak
superordinate substitution
</term>
, and
<term>
definite noun phrase reiteration
</term>
. The
<term>
system
</term>
identifies
#15498Specifically, this system is designed to deterministically choose between pronominalization, superordinate substitution, anddefinite noun phrase reiteration.
other,19-1-P84-1078,ak
cohesive text
</term>
through the use of
<term>
lexical substitutions
</term>
. Specifically , this
<term>
system
#15479This report describes Paul, a computer text generation system designed to create cohesive text through the use oflexical substitutions.
other,12-3-P84-1078,ak
antecedence recovery
</term>
for each of the
<term>
lexical substitutions
</term>
, and matches them against the
<term>
#15515The system identifies a strength of antecedence recovery for each of thelexical substitutions, and matches them against the strength of potential antecedence of each element in the text to select the proper substitutions for these elements.
tool,3-1-P84-1078,ak
reasoning
</term>
. This report describes
<term>
Paul
</term>
, a
<term>
computer text generation
#15463This report describesPaul, a computer text generation system designed to create cohesive text through the use of lexical substitutions.
other,10-2-P84-1078,ak
to deterministically choose between
<term>
pronominalization
</term>
,
<term>
superordinate substitution
#15492Specifically, this system is designed to deterministically choose betweenpronominalization, superordinate substitution, and definite noun phrase reiteration.
measure(ment),4-3-P84-1078,ak
The
<term>
system
</term>
identifies a
<term>
strength of antecedence recovery
</term>
for each of the
<term>
lexical substitutions
#15507The system identifies astrength of antecedence recovery for each of the lexical substitutions, and matches them against the strength of potential antecedence of each element in the text to select the proper substitutions for these elements.
measure(ment),20-3-P84-1078,ak
</term>
, and matches them against the
<term>
strength of potential antecedence
</term>
of each element in the
<term>
text
</term>
#15523The system identifies a strength of antecedence recovery for each of the lexical substitutions, and matches them against thestrength of potential antecedence of each element in the text to select the proper substitutions for these elements.
other,12-2-P84-1078,ak
between
<term>
pronominalization
</term>
,
<term>
superordinate substitution
</term>
, and
<term>
definite noun phrase reiteration
#15494Specifically, this system is designed to deterministically choose between pronominalization,superordinate substitution, and definite noun phrase reiteration.
tech,3-2-P84-1078,ak
substitutions
</term>
. Specifically , this
<term>
system
</term>
is designed to deterministically
#15485Specifically, thissystem is designed to deterministically choose between pronominalization, superordinate substitution, and definite noun phrase reiteration.
tech,1-3-P84-1078,ak
noun phrase reiteration
</term>
. The
<term>
system
</term>
identifies a
<term>
strength of antecedence
#15504Thesystem identifies a strength of antecedence recovery for each of the lexical substitutions, and matches them against the strength of potential antecedence of each element in the text to select the proper substitutions for these elements.
other,29-3-P84-1078,ak
antecedence
</term>
of each element in the
<term>
text
</term>
to select the proper
<term>
substitutions
#15532The system identifies a strength of antecedence recovery for each of the lexical substitutions, and matches them against the strength of potential antecedence of each element in thetext to select the proper substitutions for these elements.