Category: CMUTR
Institution: Department of Computer Science, Carnegie
        Mellon University
Abstract: Many existing natural language generation systems can be 
        characterized according to their modularization as either 
        pipelined or interleaved.
        In these separated systems, the generator is divided into 
        several modules (e.g., planning and realization), with control 
        and information passing between the modules during the 
        generation process.
        This paper proposes a third type of generator, which we can 
        integrated, that unifies the modules into a single mechanism.
        The mechanism uses a small set of orthogonal basic operation to
        produce planned and grammatical language output.
        
        Integrated systems are conceptually attractive and may support
        generation of pragmatic effects more effectively than other 
        systems.
        After discussing the advantages of the integrated approach, we
        summarize GLINDA, an integrated generator currently under
        development at Carnegie Mellon.
        GLINDA is the generator used for narration and intercharacter
        communication in the Oz Interactive Fiction and Virtual Reality
        Project.
Number: CMU-CS-92-107
Bibtype: TechReport
Month: apr
Author: Mark Kantrowitz
        Joseph Bates
Title: Integrated Natural Language Generation Systems
Year: 1992
Address: Pittsburgh, PA
Super: @CMUTR