Constraint satisfaction in logic programming
Constraint satisfaction in logic programming
Getting the message across in RST-based text generation
Current research in natural language generation
Automated discourse generation using discourse structure relations
Artificial Intelligence - Special volume on natural language processing
Customizing RST for the Automatic Production of Technical Manuals
Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
Building up rhetorical structure trees
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Computational Linguistics
Implementation architectures for natural language generation
Natural Language Engineering
From RAGS to RICHES: exploiting the potential of a flexible generation architecture
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Optimizing Referential Coherence in Text Generation
Computational Linguistics
Logical form equivalence: the case of referring expressions generation
EWNLG '01 Proceedings of the 8th European workshop on Natural Language Generation - Volume 8
An integrated framework for text planning and pronominalisation
INLG '00 Proceedings of the first international conference on Natural language generation - Volume 14
Natural Language Engineering
Generating basic skills reports for low-skilled readers*
Natural Language Engineering
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Appropriate microplanning choices for low-skilled readers
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
CICLing'03 Proceedings of the 4th international conference on Computational linguistics and intelligent text processing
| Hi-index | 0.00 |
A method is described by which a rhetorical-structure tree can be realized by a text structure made up of sections, paragraphs, sentences, vertical lists, and other textual patterns, with discourse connectives added (in the correct positions) to mark rhetorical relations. We show that text-structuring can be formulated as a Constraint Satisfaction Problem, so that all solutions respecting constraints on text-structure formation and structural compatibility can be efficiently generated. Of the many solutions generated by this method, some are stylistically preferable to others; we show how further constraints can be applied in order to select the best versions. Finally, we discuss some extensions such as the generation of indented text structures.