Building natural language generation systems
Building natural language generation systems
The Linguistic Basis of Text Generation
The Linguistic Basis of Text Generation
Describing complex charts in natural language: a caption generation system
Computational Linguistics - Special issue on natural language generation
Morphology and cross dependencies in the synthesis of personal pronouns in Romance languages
COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 1
Lessons from a failure: generating tailored smoking cessation letters
Artificial Intelligence
Implementation architectures for natural language generation
Natural Language Engineering
Using a randomised controlled clinical trial to evaluate an NLG system
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Optimizing Referential Coherence in Text Generation
Computational Linguistics
Knowledge acquisition for natural language generation
INLG '00 Proceedings of the first international conference on Natural language generation - Volume 14
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Evolving questions in text planning
INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
A dynamic programming approach to document length constraints
INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
Discourse planning for information composition and delivery: A reusable platform
Natural Language Engineering
Towards a programmable instrumented generator
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Generating tailored textual summaries from ontologies
ESWC'05 Proceedings of the Second European conference on The Semantic Web: research and Applications
| Hi-index | 0.00 |
Some types of documents need to meet size constraints, such as fitting into a limited number of pages. This can be a difficult constraint to enforce in a pipelined natural language generation (NLG) system, because size is mostly determined by content decisions, which usually are made at the beginning of the pipeline, but size cannot be accurately measured until the document has been completely processed by the NLG system. I present experimental data on the performance of single-solution pipeline, multiple-solution pipeline, and revision-based variants of the STOP system (which produces personalized smoking-cessation leaflets) in meeting a size constraint. This shows that a multiple-solution pipeline does much better than a single-solution pipeline, and that a revision-based system does best of all.