Traditionally, a generation system is divided into a message planning component and a linguistic realization component. However, such a system ignores or processes in a simplistic way too many linguistic phenomena. In order to solve this problem, an intermediate component, called micro-planner, can be added. The role of this third component is to choose the 'best' perspective that must be given to an input message. In order to achieve this, we have defined an intermediate structure, we have called textual structure, which represents in an abstract way (i.e., without taking into account linguistic details) the grammatical form of the text to be produced
Using a Textual Representation Level Component in the Context of Discourse or Dialogue Generation
1994-01-01
Abstract
Traditionally, a generation system is divided into a message planning component and a linguistic realization component. However, such a system ignores or processes in a simplistic way too many linguistic phenomena. In order to solve this problem, an intermediate component, called micro-planner, can be added. The role of this third component is to choose the 'best' perspective that must be given to an input message. In order to achieve this, we have defined an intermediate structure, we have called textual structure, which represents in an abstract way (i.e., without taking into account linguistic details) the grammatical form of the text to be producedI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
