Using a textual representational level component in the context of discourse or dialogue generation

Abstract

A natural language generation system is typically constituted by two main components: a content planning component (e.g., text planner or dialogue act planner) and a linguistic realization component. But, this is not sufficient since, on the one hand, the message built by the content pldnning component is generally not adequately detailed in order to control the many possibilities for its expression and, on the other hand, the content planner cannot influence the way in which the message will be verbalized. Generation systems require a third component, called the micro-planning (or sentence planning or phrasing) component, which acts as an intermediary between the pragmatico-semantic level and the purely syntactic level. The micro-planner is responsible for transforming the message into a textual structure. For this transformation to be achieved, grammatical and lexical resources must be selected.

Effective human-computer cooperative spoken dialogue: the AGS demonstrator

“…The natural language generation subsystem [10,9] contains a linguistic acts planner and a linguistic realizer (see also Appelt's system [1]). The former is concerned with how the intentions of the system (i.e., dialogue acts) are communicated to the user.…”

The Proof is in the Pudding

“…Some early examples (K. R. McKeown, 1985)) make a binary distinction between a strategic component that decides what to say, and a tactical component that decides how to say it. Following work has continued the idea of a spectrum from strategic to tactical but increased the number of levels to 3 (Bateman, 2002;Panaget, 1994) or even 6 (Dale & Haddock, 1991;Reiter, Sripada, Hunter, Yu, & Davy, 2005). The most fruitful framework in which to view the present work is that of Robin (1993), which uses 4: content production, content selection, content organization, and content realization.…”