Systemic Text Generation as Problem Solving (Studies in Natural Language Processing)

An exploration of a new approach to text generation that interprets systemic grammar as a computational representation. Patten demonstrates that systemic grammar can be easily and automatically translated into current AI-knowledge representations and efficiently processed by the same knowledge-based techniques currently exploited by expert systems. Thus, the fundamental methodological problem of interfacing specialized computational representations with equally specialized linguisticrepresentations can be resolved. The study provides a detailed discussion of the formal model proposed and of a substantial implementation including a relatively large systemic grammar. It represents a fundamental and productive contribution to the literature of text generation.

This study explores an approach to text generation that interprets systemic grammar as a computational representation. Terry Patten demonstrates that systemic grammar can be easily and automatically translated into current AI knowledge representations and efficiently processed by the same knowledge-based techniques currently exploited by expert systems.