Text generation: using discourse strategies and focus constraints to generate natural language text
Text generation: using discourse strategies and focus constraints to generate natural language text
Getting computers to talk like you and me
Getting computers to talk like you and me
Natural language processing: a knowledge-engineering approach
Natural language processing: a knowledge-engineering approach
Attention, intentions, and the structure of discourse
Computational Linguistics
Integrating intention and convention to organize problem-solving dialogues
Integrating intention and convention to organize problem-solving dialogues
Discourse structures for text generation
ACL '84 Proceedings of the 10th International Conference on Computational Linguistics and 22nd annual meeting on Association for Computational Linguistics
A syntactic approach to discourse semantics
ACL '84 Proceedings of the 10th International Conference on Computational Linguistics and 22nd annual meeting on Association for Computational Linguistics
Hi-index | 0.00 |
Human discourse appears coherent when it reflects coherent human thought. However, computers do not necessarily store or process information in the same way that people do and, therefore, cannot rely on the structure of their reasoning for the structure of their dialogues. Instead, computer-generated conversation must rely on some other mechanism for its organisation. In this paper, we discuss one such mechanism. We describe a template that provides a guide for conversation. The template is built from schemata representing discourse convention. As goals arrive from the problem solver they are added to the template. Because accepted discourse structures are used to connect a new goal to the existing template, goals are organised into sub-groups that follow conventional, coherent patterns of discourse. We present JUDIS, an interface to a distributed problem solver that uses this approach to organise dialogues from an incoherent stream of goals.