WIP: The Coordinated Generation of Multimodal Presentations from a Common Representation
Abstract
The task of the knowledge-based presentation system WIP is the generation of a variety of multimodal documents from an input consisting of a formal description of the communicative intent of a planned presentation. WIP generates illustrated texts that are customized for the intended audience and situation. We present the architecture of WIP and introduce as its major components the presentation planner, the layout manager, the text generator and the graphics generator. An extended notion of coherence for multimodal documents is introduced that can be used to constrain the presentation planning process. The paper focuses on the coordination of contents planning and layout that is necessary to produce a coherent illustrated text. In particular, we discuss layout revisions after contents planning and the influence of layout constraints on text generation. We show that in WIP the design of a multimodal document is viewed as a non-monotonic planning process that includes various revisions of preliminary results in order to achieve a coherent output with an optimal media mix.
Keywords
Content Planning Presentation Planner Coherence Relation Constraint Hierarchy Tree Adjoin GrammarPreview
Unable to display preview. Download preview PDF.
References
- Allgayer, J., Harbusch, K., Kobsa, A., Reddig, C, Reithinger, N. & Schmauks, D.: ‘XTRA: A Natural Language Access System to Expert Systems’, International Journal of Man-Machine Studies, 31, 161–195 (1989)CrossRefGoogle Scholar
- André, E. & Rist, T.: ‘Towards a Plan-Based Synthesis of Illustrated Documents’, Proc. of the 9th European Conference on Artificial Intelligence, 25–30 (1990)Google Scholar
- André, E. & Rist, T.: ‘Synthesizing Illustrated Documents: A Plan-Based Approach’, Proc. of Info Japan 90, vol. 2, 163–170 (1990)Google Scholar
- Bandyopadhyay, S.: ‘Towards an Understanding of Coherence in Multimodal Discourse’. Technical Memo DFKI-TM-90-01, German Research Center for Artificial Intelligence, Saarbrücken Site (1990)Google Scholar
- Beach, R. J.: ‘Setting Tables and Illustrations with Style’, Xerox PARC, Technical Report CSL-85-3 (1985)Google Scholar
- Borning, A. & Duisberg, A.: ‘Constraint-Based Tools for Building User Interfaces’, ACM Trans. on Graphics, 5, 6, 345–374 (1986)CrossRefGoogle Scholar
- Borning, A., Freeman-Benson, B. & Wilson, M.: ‘Constraint Hierarchies’, Internal Report, Department of Computer Science and Engineering, FR-35, University of Washington, Seattle (1989)Google Scholar
- Feiner, S.: ‘A Grid-Based Approach to Automating Display Layout’, Proc. Graphics Interface +88, Palo Alto, Morgan Kaufmann, 192–197 (1988)Google Scholar
- Feiner, S. & McKeown, K.: ‘Coordinating Text and Graphics in Explanation Generation’, DARPA Speech and Natural Language Workshop (1989)Google Scholar
- Finkler, W. & Neumann, G.: ‘POPEL-HOW: A Distributed Parallel Model for Incremental Natural Language Production with Feedback’, Proc. of the 11th IJCAI, 1518–1523 (1989)Google Scholar
- Freeman-Benson, B., Maloney, J. & Borning, A.: ‘An Incremental Constraint Solver’, Communications of the ACM, 33, 1, 54–63 (1990)CrossRefGoogle Scholar
- Graf, W.: ‘Spezielle Aspekte des automatischen Layout-Designs bei der koordinierten Generierung von multimodalen Dokumenten’, GI-Workshop Multimediale elektronische Dokumente (1990)Google Scholar
- Grice, H.: ‘Logic and Conversation’. In Cole and Morgan (eds.), Syntax and Semantics, 3, New York, Academic Press (1975)Google Scholar
- Grimes, J.E.: The Thread of Discourse. The Hague, Mouton (1975)Google Scholar
- Harbusch, K.: ‘Constraining Tree Adjoining Grammars by Unification’, Proc. of the 13th COLING, 167–172 (1990)Google Scholar
- Hobbs, J.: ‘Coherence and Coreference’, Cognitive Science, 3, 1 (1979)MathSciNetCrossRefGoogle Scholar
- Hobbs, J.: ‘Why is Discourse Coherent?’. In Neubauer (ed.), Coherence in Natural Language Texts, Hamburg, Buske (1983)Google Scholar
- Jameson, A. & Wahlster, W.: ‘User Modelling in Anaphora Generation: Ellipsis and Definite Description’, Proc. of the 5th ECAI, 222–221 (1982)Google Scholar
- Kjorup, S.: ‘Pictorial Speech Acts’, Erkenntnis, 12, 55–71 (1978)CrossRefGoogle Scholar
- Mann, W. & Thompson, S.: ‘Rhetorical Structure Theory: Towards a Functional Theory of Text Organization’, TEXT, 8, 3 (1988)Google Scholar
- Marks, J. & Reiter, E.: ‘Avoiding Unwanted Conversational Implicatures in Text and Graphics’, Proc. of the 8th AAAI, 450–455 (1990)Google Scholar
- Maaß, W.: ‘Constraint-basierte Repräsentation von graphischem Wissen am Beispiel des Layout-Managers in WIP’. MS thesis, Computer Science Departement, University of Saarbrücken (1991)Google Scholar
- McKeown, K. & Feiner, S.: ‘Interactive Multimedia Explanation for Equipment Maintenance and Repair’, DARPA Speech and Natural Language Workshop, 42–47 (1990)Google Scholar
- Moore, J. & Paris, C: ‘Planning Text for Advisory Dialogues’, Proc. of the 27th ACL, 203–211 (1989)Google Scholar
- Moore, J.D. & Swartout, W.R.: ‘A Reactive Approach to Explanation’, Proc. of the 11th IJCAI, 1504–1510 (1989)Google Scholar
- Müller-Brockmann, J.: Grid Systems in Graphic Design. Stuttgart, Hatje (1981)Google Scholar
- Neal, J. & Shapiro, S.: ‘Intelligent Multi-Media Interface Technology’, Proc. of the Workshop on Architectures of Intelligent Interfaces: Elements & Prototypes, 69–91 (1988)Google Scholar
- Nebel, B.: ‘Reasoning and Revision in Hybrid Representation Systems’, Lecture Notes in AI, 422, Berlin, Springer-Verlag (1990)Google Scholar
- Reichmann, R.: Getting Computers to Talk like You and Me. Cambridge, MA, MIT Press (1985)Google Scholar
- Rist, T. & André, E.: ‘Wissensbasierte Perspektivenwahl für die automatische Erzeugung von 3D-Objektdarstellungen’ In Kansy, K. and Wißkirchen P. (eds.), Graphik und KL IFB 239, Berlin, Springer-Verlag, 48–57 (1990)CrossRefGoogle Scholar
- Roth, S., Mattis, J. & Mesnard, X.: ‘Graphics and Natural Language as Components of Automatic Explanation’, Proc. of the Workshop on Architectures of Intelligent Interfaces: Elements & Prototypes, 109–128 (1988)Google Scholar
- Searle, J.: Speech Acts: An Essay in the Philosophy of Language. Cambridge, MA., Cambridge University Press (1969)CrossRefGoogle Scholar
- Schauder, A.: ‘Inkrementelle syntaktische Generierung natürlicher Sprache mit Tree Adjoining Grammars’. MS thesis, Computer Science Departement, University of Saarbrücken (1990)Google Scholar
- Stock, O.: ‘Natural Language and Exploration of an Information Space: the ALFresco Interactive System’. Proceedings of the 12th IJCAI, 972–978 (1991)Google Scholar
- van Dijk, T.: Textwissenschaft. München, DTV (1980)CrossRefGoogle Scholar
- Wahlster, W.: ‘User and Discourse Models for Multimodal Communication’. In Sullivan, J. and Tyler, S. (eds.), Architectures for Intelligent User Interfaces: Elements & Prototypes, Reading, MA., Addison-Wesley (1991)Google Scholar
- Wahlster, W. & Kobsa, A.: ‘User Models in Dialog Systems’. In Kobsa, A. and Wahlster, W. (eds.), User Models in Dialog Systems, Symbolic Computation Series, Berlin, Springer-Verlag, 4–34 (1989)CrossRefGoogle Scholar
- Wahlster, W., André, E., Hecking, M. & Rist, T.: ‘WIP: Knowledge-based Presentation of Information’. Report WIP-1, German Research Center for Artificial Intelligence, Saarbrücken (1989)Google Scholar
- Wahlster, W., André, E., Graf, W. & Rist, T.: ‘Designing Illustrated Texts: How Language Production Is Influenced by Graphics Generation’, Proc. of the 5th Conference of the European Chapter of the ACL, Berlin, Springer-Verlag, 8–14 (1991)Google Scholar