BibTeX
@TECHREPORT{Stent98aspectsof,
author = {Amanda J. Stent},
title = {Aspects of Natural Language Generation},
institution = {},
year = {1998}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Natural language generation is a knowledge-intensive, goal-directed process involving many interacting choices. Some questions that a generation system must answer include: ffl what information needs to be included in the output to satisfy the speaker's or writer's communicative goals? ffl how should a discourse contribution be structured to ensure its coherence? ffl which modalities should be used to maximize the information exchange? ffl how can output be tailored to specific users? In this paper, we examine some aspects of natural language generation that constrain the planning process, including theories of discourse structure, models of discourse context and of users, and multimodal generation. This work was supported by ONR research grant N00014-95-1-1088, U.S. Air Force/Rome Labs research contract no. F30602-95-1-0025, NSF research grant no. IRI-9623665 and Columbia University/NSF research grant no. OPG: Contents 1 Introduction 4 1.1 What is Natural Language Generation? ...
Keyphrases
natural language generation specific user goal-directed process planning process nsf research grant onr research grant n00014-95-1-1088 discourse contribution discourse context communicative goal generation system multimodal generation discourse structure columbia university nsf research grant information exchange many interacting choice
