Building natural language generation systems
Building natural language generation systems
Generating English summaries of time series data using the Gricean maxims
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations
Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations
Game Theory and Linguistic Meaning
Game Theory and Linguistic Meaning
Towards a game-theoretic approach to content determination
ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation
Hi-index | 0.00 |
In order to satisfy the informational demands of different users, generated texts should be tailored to the respective user types. Document planning may benefit from a formal modeling of the participating agents (the generation system and the user) within the framework of game theory. We show how rhetorical structures map to speaker strategies, and how a user model may be represented as a domain theory, containing different hypotheses for the listener strategies. Based on this, we present an algorithm which simultaneously performs the tasks of message selection and document structuring.