Knowledge intensive natural language generation with revision
Knowledge intensive natural language generation with revision
Generating high-level structure for extended explanations (vols. I and II)
Generating high-level structure for extended explanations (vols. I and II)
Artificial Intelligence
Aggregation in Natural Language Generation
EWNLG '93 Selected papers from the Fourth European Workshop on Trends in Natural Language Generation, An Artificial Intelligence Perspective
Integrated Natural Language Generation Systems
Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
Floating constraints in lexical choice
Computational Linguistics
DiMLex: a lexicon of discourse markers for text generation and understanding
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Integrating text plans for conciseness and coherence
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Dynamically improving explanations: a revision-based approach to explanation generation
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Parenthetical constructions: an argument against modularity
GEAF '09 Proceedings of the 2009 Workshop on Grammar Engineering Across Frameworks
Unlocking medical ontologies for non-ontology experts
BioNLP '11 Proceedings of BioNLP 2011 Workshop
Automatic verbalisation of SNOMED classes using OntoVerbal
AIME'11 Proceedings of the 13th conference on Artificial intelligence in medicine
Hi-index | 0.00 |
Pipelined Natural Language Generation (NLG) systems have grown increasingly complex as architectural modules were added to support language functionalities such as referring expressions, lexical choice, and revision. This has given rise to discussions about the relative placement of these new modules in the overall architecture. Recent work on another aspect of multi-paragraph text, discourse markers, indicates it is time to consider where a discourse marker insertion algorithm fits in. We present examples which suggest that in a pipelined NLG architecture, the best approach is to strongly tie it to a revision component. Finally, we evaluate the approach in a working multi-page system.