Natural language generation from plans
Computational Linguistics
A problem for RST: the need for multi-level discourse analysis
Computational Linguistics
The effect of resource limits and task complexity on collaborative planning in dialogue
Artificial Intelligence - Special volume on empirical methods
A Model for Adapting Explanations to the User‘s Likely Inferences
User Modeling and User-Adapted Interaction
Textual Relations as Part of Multiple Links Between Text Segments
EWNLG '93 Selected papers from the Fourth European Workshop on Trends in Natural Language Generation, An Artificial Intelligence Perspective
Type-Driven Suppression of Redundancy in the Generation of Inference-Rich Reports
Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
Reconstruction Proofs at the Assertion Level
CADE-12 Proceedings of the 12th International Conference on Automated Deduction
Computer generation of multiparagraph English text
Computational Linguistics
Lexical choice criteria in language generation
EACL '93 Proceedings of the sixth conference on European chapter of the Association for Computational Linguistics
A hybrid reasoning model for indirect answers
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Exploiting the addressee's inferential capabilities in presenting mathematical proofs
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Proof verbalization as an application of NLG
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
AISC '00 Revised Papers from the International Conference on Artificial Intelligence and Symbolic Computation
Presenting Proofs in a Human-Oriented Way
CADE-16 Proceedings of the 16th International Conference on Automated Deduction: Automated Deduction
Presenting Mathematical Concepts as an Example for Inference-Rich Domains
NLDB '00 Proceedings of the 5th International Conference on Applications of Natural Language to Information Systems-Revised Papers
Presenting inequations in mathematical proofs
Information Sciences: an International Journal
| Hi-index | 0.00 |
The majority of generation systems to date are able to communicate information only by uttering it explicitly. Rhetorical Structure Theory (RST), one of the most frequently used discourse theories for text planning in natural language generation, does not support more flexibility either, because it ignores implicit rhetorical relations and accepts only one prominent relation between clauses. In formal systems, however, the underlying information is represented in a very detailed way, which requires easily inferable parts to be left implicit for producing natural and comprehensible discourse. In order to improve the quality of texts generated from fine-grained semantic specifications, we present an approach that successively revises an explicit text plan by introducing addressee dependent short-cuts and communicatively justified reorganizations. Text plan revisions include the compactification of stateaction and reasoning sequences, the omission of redundant conditions, and the reorganization of arguments for presentation purposes. Our techniques enable us to generate shorter and better understandable texts from detailed representations, as in formal systems, especially in deduction systems.