Generating customized text and graphics in the COMET explanation testbed

Michael Elhadad, Steven Feiner, Kathleen McKeown, Doree Seligmann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations


It is shown how COMET, a system that uses natural language and graphics generation components to produce the text and pictures of its explanations dynamically, can create a variety of different explanations to explain the same concepts, and thus better meets the needs of different users. The authors focus on four ways in which COMET produces different explanations for the same concepts, describing how it is influenced by the plan containing the concept, by user background knowledge, by previous dialogue, and by interactive exploration of an explanation.

Original languageEnglish
Title of host publicationWinter Simulation Conference Proceedings
PublisherPubl by IEEE
Number of pages8
ISBN (Print)078030181X
StatePublished - 1 Dec 1991
Event1991 Winter Simulation Conference Proceedings - Phoenix, AZ, USA
Duration: 8 Dec 199111 Dec 1991

Publication series

NameWinter Simulation Conference Proceedings
ISSN (Print)0275-0708


Conference1991 Winter Simulation Conference Proceedings
CityPhoenix, AZ, USA

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Safety, Risk, Reliability and Quality
  • Chemical Health and Safety
  • Applied Mathematics


Dive into the research topics of 'Generating customized text and graphics in the COMET explanation testbed'. Together they form a unique fingerprint.

Cite this