Discourse strategies for generating natural-language text
Artificial Intelligence
Attention, intentions, and the structure of discourse
Computational Linguistics
Pragmatics and natural language generation
Artificial Intelligence
An analysis of explanation and its implications for the design of explanation planners
An analysis of explanation and its implications for the design of explanation planners
Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
A reactive approach to explanation in expert and advice-giving systems
A reactive approach to explanation in expert and advice-giving systems
Generating explanatory discourse: a plan-based, interactive approach
Generating explanatory discourse: a plan-based, interactive approach
A computational theory of goal-directed style in syntax
Computational Linguistics
Hi-index | 0.00 |
The paper summarizes an ongoing investigation of the discourse planning tasks concerned with the sequencing of utterances and their parts. Content selection provides some important constraints on sequencing, most notably those derived from the preconditions and effects of planning operators. However these operators underconstrain sequencing, especially below the granularity at which they interface with a domain knowledge source. Further constraints are available from the integrative processes of the hearer or reader and from working memory limits. Application of these constraints is a matter for discourse planning because the choices relate to one's communicative goals. The planning task is one of translating functionally relevant relationships between units to be ordered into ordering constraints. A collection of strategies for this task are presented. Some of the strategies were used in an earlier implemented system; many are justified by prior psycholinguistic research. Also discussed include current efforts to extend the work to focus structure in general, and to address the handling of conflicts between strategies.