Constraint-based conversion of fiction text to a time-based graphical representation

This paper presents a method for converting unrestricted fiction text into a time-based graphical form. Key concepts extracted from the text are used to formulate constraints describing the interaction of entities in a scene. The solution of these constraints over their respective time intervals provides the trajectories for these entities in a graphical representation. Three types of entity are extracted from fiction books to describe the scene, namely Avatars, Areas and Objects. We present a novel method for modeling the temporal aspect of a fiction story using multiple time-line representations after which the information extracted regarding entities and time-lines is used to formulate constraints. A constraint solving technique based on interval arithmetic is used to ensure that the behaviour of the entities satisfies the constraints over multiple universally quantified time intervals. This approach is demonstrated by finding solutions to multiple time-based constraints, and represents a new contribution to the field of Text-to-Scene conversion. An example of the automatically produced graphical output is provided in support of our constraint-based conversion scheme.

[1]  Hans Svensson,et al.  CarSim: An Automatic 3D Text-to-Scene Conversion System Applied to Road Accident Reports , 2003, EACL.

[2]  F. Kenton Musgrave,et al.  The synthesis and rendering of eroded fractal terrains , 1989, SIGGRAPH.

[3]  Pascal Müller.  Procedural modeling of cities , 2006, SIGGRAPH Courses.

[4]  Jane Wilhelms,et al.  Put: language-based interactive manipulation of objects , 1996, IEEE Computer Graphics and Applications.

[5]  Roger C. Schank,et al.  The fourteen primitive actions and their inferences. , 1973 .

[6]  Paul McKevitt,et al.  Using lexical knowledge of verbs in language-to-vision applications , 2004 .

[7]  Frank Jardillier,et al.  Screen‐Space Constraints for Camera Movements: the Virtual Cameraman , 1998, Comput. Graph. Forum.

[8]  Ruqian Lu,et al.  Automatic generation of computeranimation: using AI for movie animation , 2002 .

[9]  Masoud Yazdani,et al.  Language visualisation: Applications and theoretical foundations of a primitive-based approach , 1995, Artificial Intelligence Review.

[10]  Shaun Bangay,et al.  Hierarchical rule generalisation for speaker identification in fiction books , 2006 .

[11]  D. M. Allester.  Clp(intervals) Revisited Clp(intervals) Revisited 1 , 1994 .

[12]  Richard Sproat,et al.  WordsEye: an automatic text-to-scene conversion system , 2001, SIGGRAPH.

[13]  Marc Christie,et al.  Interval constraint solving for camera control and motion planning , 2000, TOCL.

[14]  Richard Johansson,et al.  Automatic Text-to-Scene Conversion in the Traffic Accident Domain , 2005, IJCAI.

[15]  Nina Wacholder,et al.  Disambiguation of Proper Names in Text , 1997, ANLP.

[16]  Frédéric Goualard,et al.  Revising Hull and Box Consistency , 1999, ICLP.

[17]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .