Image Schemas and Conceptual Dependency Primitives: A Comparison

A major challenge in natural language understanding research in artificial intelligence (AI) has been and still is the grounding of symbols in a representation that allows for rich semantic interpretation, inference, and deduction. Across cognitive linguistics and other disciplines, a number of principled methods for meaning representation of natural language have been proposed that aim to emulate capacities of human cognition. However, little cross-fertilization among those methods has taken place. A joint effort of human-level meaning representation from AI research and from cognitive linguistics holds the potential of contributing new insights to this profound challenge. To this end, this paper presents a first comparison of image schemas to an AI meaning representation system called Conceptual Dependency (CD). Restricting our study to the domain of physical and spatial conceptual primitives, we find connections and mappings from a set of action primitives in CD to a remarkably similar set of image schemas. We also discuss important implications of this connection, from formalizing image schemas to improving meaning representation systems in AI.

[1]  Beate Hamp,et al.  The Fundamental System of Spatial Schemas in Language , 2022 .

[2]  Hector J. Levesque,et al.  On our best behaviour , 2014, Artif. Intell..

[3]  Roger C. Schank,et al.  Conceptual dependency: A theory of natural language understanding , 1972 .

[4]  Roger C. Schank,et al.  Conceptual Information Processing , 2014 .

[5]  Jean M. Mandler,et al.  On defining image schemas , 2014, Language and Cognition.

[6]  G. Lakoff,et al.  Where mathematics comes from : how the embodied mind brings mathematics into being , 2002 .

[7]  J. Mandler.  How to build a baby: II. Conceptual primitives. , 1992, Psychological review.

[8]  Jean M. Mandler,et al.  The spatial foundations of the conceptual system , 2010, Language and Cognition.

[9]  G. Lakoff,et al.  Women, Fire, and Dangerous Things: What Categories Reveal about the Mind , 1988 .

[10]  Steven L. Lytinen,et al.  CONCEPTUAL DEPENDENCY AND ITS DESCENDANTS , 1992 .

[11]  Fabian Neuhaus,et al.  Choosing the Right Path: Image Schema Theory as a Foundation for Concept Invention , 2015, J. Artif. Gen. Intell..

[12]  Till Mossakowski,et al.  Between Contact and Support: Introducing a Logic for Image Schemas and Directed Movement , 2017, AI*IA.

[13]  Jamie C. Macbeth,et al.  Crowdsourcing a Parallel Corpus for Conceptual Analysis of Natural Language , 2017, HCOMP.

[14]  Richard Socher,et al.  Ask Me Anything: Dynamic Memory Networks for Natural Language Processing , 2015, ICML.

[15]  R. Schank,et al.  Inside Computer Understanding: Five Programs Plus Miniatures , 1982 .

[16]  R. Wallace.  The Body in the Mind: The Bodily Basis of Meaning, Imagination, and Reason , 1988 .

[17]  B. Landau,et al.  Starting at the end: the importance of goals in spatial language , 2005, Cognition.

[18]  Vyvyan Evans,et al.  Cognitive Linguistics: An Introduction , 2001 .

[19]  Werner Kuhn,et al.  An Image-Schematic Account of Spatial Categories , 2007, COSIT.

[20]  Roger C. Schank,et al.  Scripts, plans, goals and understanding: an inquiry into human knowledge structures , 1978 .

[21]  George Lakoff.  Image Schemas: From Linguistic Analysis to Neural Grounding , 2005 .

[22]  Patrick Henry Winston.  The Genesis Story Understanding and Story Telling System A 21 st Century Step toward Artificial Intelligence , 2014 .

[23]  Jean M. Mandler,et al.  A summary of The foundations of mind: Origins of conceptual thought , 2004 .

[24]  Maria M. Hedblom,et al.  Kinesthetic Mind Reader : A Method to Identify Image Schemas in Natural Language , 2017 .

[25]  Marco Schorlemmer,et al.  The Yoneda Path to the Buddhist Monk Blend , 2016, JOWO@FOIS.

[26]  Christopher D. Manning.  Computational Linguistics and Deep Learning , 2015, Computational Linguistics.

[27]  P. Langley.  Intelligent Behavior in Humans and Machines , 2012 .

[28]  Brandon Bennett,et al.  Corpus Guided Sense Cluster Analysis: a methodology for ontology development (with examples from the spatial domain) , 2014, FOIS.