Text generation: using discourse strategies and focus constraints to generate natural language text
Text generation: using discourse strategies and focus constraints to generate natural language text
Tailoring object descriptions to a user's level of expertise
Computational Linguistics - Special issue on user modeling
Generating context-sensitive responses to object-related misconceptions
Artificial Intelligence
Pragmatics and natural language generation
Artificial Intelligence
Explanation and interaction: the computer generation of explanatory dialogues
Explanation and interaction: the computer generation of explanatory dialogues
Automated discourse generation using discourse structure relations
Artificial Intelligence - Special volume on natural language processing
An analysis of explanation and its implications for the design of explanation planners
An analysis of explanation and its implications for the design of explanation planners
Participating in explanatory dialogues: interpreting and responding to questions in context
Participating in explanatory dialogues: interpreting and responding to questions in context
Revision-based generation of natural language summaries providing historical background: corpus-based analysis, design, implementation and evaluation
Generating natural language explanations from large-scale knowledge bases
Generating natural language explanations from large-scale knowledge bases
AI Research in the Context of a Multifunctional Knowledge Base: The BotanyKnowledge Base Project
AI Research in the Context of a Multifunctional Knowledge Base: The BotanyKnowledge Base Project
Generating natural language descriptions with integrated text and examples
Generating natural language descriptions with integrated text and examples
Afterword: from this revolution to the next
Smart machines in education
A representation for comparing simulations and computing the purpose of geometric features
Artificial Intelligence for Engineering Design, Analysis and Manufacturing
CogentHelp: NLG meets SE in a tool for authoring dynamically generated on-line help
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Building Intelligent Interactive Tutors: Student-centered strategies for revolutionizing e-learning
Building Intelligent Interactive Tutors: Student-centered strategies for revolutionizing e-learning
Hi-index | 0.00 |
To explain complex phenomena, an explanation system must be able to select information from a formal representation of domain knowledge, organize the selected information into multisentential discourse plans, and realize the discourse plans in text. Although recellit years have witnessed significant progress in the development of sophisticated computational mechanisms for explanation, empirical results have been limited. This paper reports on a seven year effort to empirically study explanation generation from semantically rich, large-scale knowledge bases. We first describe Knight, a robust explanation system that constructs multi-sentential and multi-paragraph explanations from the Biology Knowledge Base, a large-scale knowledge base in the domain of botanical anatomy, physiology, and development. We then introduce the Two Panel evaluation methodology and describe how Knight's performance was assessed with this methodology in the most extensive empirical evaluation conducted on an explanation system. In this evaluation, Knight scored within "half a grade" of domain experts, and its performance exceeded that of one of the domain experts.