</term>
has been used for
<term>
AI text generation
#15542The 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 the text to select the proper substitutions for these elements. Systemic grammar has been used for AI text generation work in the past, but the implementations have tended be ad hoc or inefficient.
lr,20-2-E85-1037,ak
applied directly to an unadulterated
<term>
systemic grammar
</term>
. This approach is made possible
#15587This paper presents an approach to systemic text generation where AI problem solving techniques are applied directly to an unadulterated systemic grammar .
other,10-3-E85-1037,ak
by a special relationship between
<term>
systemic grammar
</term>
and
<term>
problem solving
</term>
:
#15600This approach is made possible by a special relationship between systemic grammar and problem solving: both are organized primarily as choosing from alternatives.
other,12-4-E85-1037,ak
generation
</term>
firmly based in a
<term>
linguistic theory
</term>
. We propose a draft scheme of the
#15627The result is simple, efficient text generation firmly based in a linguistic theory .