Presentations (Communicative Events)

Frame-Based Representation of Lexical, Graphical, and Factual Knowledge for Text-to-Scene Generation

Bauer, Daniel; Coyne, Robert Eric; Rambow, Owen C.

We outline ongoing work on WordsEye, a text-to-scene generation system. While WordsEye (Coyne and Sproat, 2001) currently recognizes descriptions of simple spatial relations between objects, we are aiming to add support for complex actions, events and states-of-affairs. To this end we use frame-based representations for both asserted and terminological knowledge. The resulting scenes are static spatial arrangements of pre-existing 3D models.


  • thumnail for Bauer_Coyne_Rambow-abstract.pdf Bauer_Coyne_Rambow-abstract.pdf application/pdf 123 KB Download File

More About This Work

Academic Units
Computer Science
Center for Computational Learning Systems
Concept Types and Frames in Language, Cognition, and Science (CTF), 2012
Published Here
August 2, 2013