Attention, intentions, and the structure of discourse
Computational Linguistics
Discourse strategies for generating natural-language text
Readings in natural language processing
IPF: an incremental parallel formulator
Current research in natural language generation
Participating in explanatory dialogues: interpreting and responding to questions in context
Participating in explanatory dialogues: interpreting and responding to questions in context
Empirically designing and evaluating a new revision-based model for summary generation
Artificial Intelligence - Special volume on empirical methods
Building natural language generation systems
Building natural language generation systems
Designing Web Usability: The Practice of Simplicity
Designing Web Usability: The Practice of Simplicity
User Modeling in Text Generation
User Modeling in Text Generation
Generating Natural Language under Pragmatic Constraints
Generating Natural Language under Pragmatic Constraints
Artificial Believers: The Ascription of Belief
Artificial Believers: The Ascription of Belief
Integrating Text Planning and Linguistic Choice by Annotating Linguistic Structures
Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
Pipelines and size constraints
Computational Linguistics
Planning texts by constraint satisfaction
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Tailoring the Content of Dynamically Generated Explanations
UM '01 Proceedings of the 8th International Conference on User Modeling 2001
The Impact of Empirical Studies on the Design of an Adaptive Hypertext Generation System
Revised Papers from the nternational Workshops OHS-7, SC-3, and AH-3 on Hypermedia: Openness, Structural Awareness, and Adaptivity
Tailoring Automatically Generated Hypertext
User Modeling and User-Adapted Interaction
Using HLT for acquiring, retrieving and publishing knowledge in AKT: position paper
HLTKM '01 Proceedings of the workshop on Human Language Technology and Knowledge Management - Volume 2001
Statistical acquisition of content selection rules for natural language generation
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Reuse and challenges in evaluating language generation systems: position paper
Evalinitiatives '03 Proceedings of the EACL 2003 Workshop on Evaluation Initiatives in Natural Language Processing: are evaluation methods, metrics and resources reusable?
Hi-index | 0.00 |
The majority of existing language generation systems have a pipeline architecture which offers efficient sequential execution of modules, but does not allow decisions about text content to be revised in later stages. However, as exemplified in this paper, in some cases choosing appropriate content can depend on text length and formatting, which in a pipeline architecture are determined after content planning is completed. Unlike pipelines, interleaved and revision-based architectures can deal with such dependencies but tend to be more expensive computationally. Since our system needs to generate acceptable hypertext explanations reliably and quickly, the pipeline architecture was modified instead to allow additional content to be requested in later stages of the generation process if necessary.