Using Quantitative Information to Improve Analogical Matching Between Sketches

Qualitative representations are suitable for sketch understanding systems because they highlight important relationships while leaving out details that are not essential for conceptual understanding. These representations can be used to perform spatial analogies between sketches, which determine qualitative similarities and differences. However, there are cases where including quantitative information is necessary for accurately representing a sketch. We describe a method for using quantitative information to constrain qualitative spatial analogies. The utility of this method is demonstrated in the context of a sketch based educational software system. Importantly, using quantitative information to improve analogical matches is not domain specific. It can be used in any situation where qualitative and quantitative spatial information must be combined to accurately interpret a sketch. This approach has the potential to improve sketch understanding in educational software applications for highly spatial domains.

[1]  Herbert A. Simon,et al.  Why a diagram is (sometimes) worth 10, 000 word , 1987 .

[2]  Benjamin D. Jee,et al.  Drawing on Experience: Use of Sketching to Evaluate Knowledge of Spatial Scientific Concepts , 2009 .

[3]  Benjamin D. Jee,et al.  Sketch Worksheets: A Sketch-Based Educational Software System , 2010, IAAI.

[4]  Brian Falkenhainer,et al.  An Examination of the Third Stage in the Analogy Process: Verification-based Analogical Learning , 1987, IJCAI.

[5]  L. Hedges,et al.  Categories and particulars: prototype effects in estimating spatial location. , 1991, Psychological review.

[6]  Shaaron E. Ainsworth,et al.  Drawing to Learn in Science , 2011, Science.

[7]  D. Gentner.  Structure‐Mapping: A Theoretical Framework for Analogy* , 1983 .

[8]  K. Holyoak,et al.  A symbolic-connectionist theory of relational inference and generalization. , 2003, Psychological review.

[9]  Thomas F. Stahovich,et al.  Newton's Pen: A pen-based tutoring system for statics , 2008, Comput. Graph..

[10]  Anthony G. Cohn,et al.  Qualitative Spatial Representation and Reasoning with the Region Connection Calculus , 1997, GeoInformatica.

[11]  Thomas F. Stahovich,et al.  Kirchhoff's Pen: a pen-based circuit analysis tutor , 2007, SBIM '07.

[12]  Brian Falkenhainer,et al.  The Structure-Mapping Engine: Algorithm and Examples , 1989, Artif. Intell..

[13]  Herbert A. Simon,et al.  Why a Diagram is (Sometimes) Worth Ten Thousand Words , 1987 .

[14]  Ann C. H. Kindfleld.  Expert Diagrammatic Reasoning in Biology * , 2002 .

[15]  Kenneth D. Forbus,et al.  CogSketch: Sketch Understanding for Cognitive Science Research and for Education , 2011, Top. Cogn. Sci..

[16]  Tracy Anne Hammond,et al.  LAMPS: A sketch recognition-based teaching tool for Mandarin Phonetic Symbols I , 2010, J. Vis. Lang. Comput..

[17]  Bradley C. Love,et al.  CAB: Connectionist Analogy Builder , 2003, Cogn. Sci..

[18]  Thomas F. Stahovich,et al.  Proceedings of the 4th Eurographics workshop on Sketch-based interfaces and modeling , 2007 .

[19]  Kenneth D. Forbus,et al.  Making SME greedy and pragmatic , 2006 .

[20]  Dirk van Rijn,et al.  Proceedings of the 31st annual conference of the Cognitive Science Society , 2003 .

[21]  Herbert A. Simon,et al.  Why a Diagram is (Sometimes) Worth Ten Thousand Words , 1987, Cogn. Sci..

[22]  G CohnAnthony,et al.  Qualitative Spatial Representation and Reasoning with the Region Connection Calculus , 1997 .