Specifying composite illustrations with communicative goals
UIST '89 Proceedings of the 2nd annual ACM SIGGRAPH symposium on User interface software and technology
Natural language generation in COMET
Current research in natural language generation
Automated generation of intent-based 3D Illustrations
Proceedings of the 18th annual conference on Computer graphics and interactive techniques
Intelligent multi-media interface technology
Intelligent user interfaces
Graphics and natural language as components of automatic explanation
Intelligent user interfaces
Dynamic 3D illustrations with visibility constraints
Scientific visualization of physical phenomena
Planning English Sentences
Automatic graphics environment synthesis
Automatic graphics environment synthesis
Generating spatial descriptions for cross-modal references
ANLC '92 Proceedings of the third conference on Applied natural language processing
Types in Functional Unification Grammars
ACL '90 Proceedings of the 28th annual meeting on Association for Computational Linguistics
Combining deictic gestures and natural language for referent identification
COLING '86 Proceedings of the 11th coference on Computational linguistics
Computer Standards & Interfaces
CICLing'06 Proceedings of the 7th international conference on Computational Linguistics and Intelligent Text Processing
Hi-index | 0.00 |
When explanations include multiple media, such as text and illustrations, a reference to an object can be made through a combination of media. We call part of a presentation that references material elsewhere a cross-reference. We are concerned here with how textual expressions can refer to parts of accompanying illustrations. The illustration to which a cross-reference refers should also satisfy the specific goal of identifying an object for the user. Thus, producing an effective cross-reference not only involves text generation, but may also entail modifying or replacing an existing illustration and in some cases, generating an illustration where previously none was needed. In this paper, we describe the different types of cross-references that COMET (COordinated Multimedia Explanation Testbed) generates and show the roles that both its text and graphics generators play in this process.