The Symbol Grounding Problem

Abstract

How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their (arbitrary) shapes, be grounded in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations must be grounded bottom-up in nonsymbolic representations of two kinds: (1) "iconic representations," which are analogs of the proximal sensory projections of distal objects and events, and (2) "categorical representations," which are learned and innate feature-detectors that pick out the invariant features of object and event categories from their sensory projections. Elementary symbols are the names of these object and event categories, assigned on the basis of their (nonsymbolic) categorical representations. Higher-order (3) "symbolic representations," grounded in these elementary symbols, consist of symbol strings describing category membership relations (e.g., "An X is a Y that is Z").

Cited by in corpus (51)

• Multi-Modal Knowledge Graph Construction and Application: A Survey
• Logic Tensor Networks
• Semantic information, autonomous agency, and nonequilibrium statistical physics
• Symbol Emergence in Robotics: A Survey
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
• A Survey of Knowledge Representation in Service Robotics
• Symbol Emergence in Cognitive Developmental Systems: a Survey
• Cultural Cartography with Word Embeddings
• Where to put the Image in an Image Caption Generator
• DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self
• Neurosymbolic Reinforcement Learning and Planning: A Survey
• Philosophical Specification of Empathetic Ethical Artificial Intelligence
• Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different Levels of Representation
• Language Bootstrapping: Learning Word Meanings From Perception-Action Association
• Improving Grounded Natural Language Understanding through Human-Robot Dialog
• Symbol Emergence and The Solutions to Any Task
• Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models
• An evolutionary process without variation and selection
• Is there a future for AI without representation?
• On the Computation of Meaning, Language Models and Incomprehensible Horrors
• Large language models and linguistic intentionality
• Multimodal Hierarchical Dirichlet Process-based Active Perception
• Emergent Causality and the Foundation of Consciousness
• Building the Observer into the System: Toward a Realistic Description of Human Interaction with the World
• Operationalising Representation in Natural Language Processing
• A Thorough Formalization of Conceptual Spaces
• Robot Navigation in Unseen Spaces using an Abstract Map
• Analyzing Differentiable Fuzzy Logic Operators
• Conceptual Organization is Revealed by Consumer Activity Patterns
• The Artificial Scientist: Logicist, Emergentist, and Universalist Approaches to Artificial General Intelligence
• Feature Guided Search for Creative Problem Solving Through Tool Construction
• Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions
• The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest
• Instantiation
• Symbol grounding in computational systems: A paradox of intentions
• Who is Responsible When AI Fails? Mapping Causes, Entities, and Consequences of AI Privacy and Ethical Incidents
• What the F*ck Is Artificial General Intelligence?
• Robots Learning to Say `No': Prohibition and Rejective Mechanisms in Acquisition of Linguistic Negation
• Formalized Conceptual Spaces with a Geometric Representation of Correlations
• Semi-supervised Multimodal Representation Learning through a Global Workspace
• Guided Navigation from Multiple Viewpoints using Qualitative Spatial Reasoning
• Bootstrapping Concept Formation in Small Neural Networks
• A Brain-Inspired Sequence Learning Model based on a Logic
• A consequence of failed sequential learning: A computational account of developmental amnesia
• SAILOR: Perceptual Anchoring For Robotic Cognitive Architectures
• A Signal-Centric Perspective on the Evolution of Symbolic Communication
• Cognitive algorithms and systems of episodic memory, semantic memory and their learnings
• Embodied GPT-5.1: Evidence of a World Model?
• Formal Ways for Measuring Relations between Concepts in Conceptual Spaces
• Human-Robot Dialogue Annotation for Multi-Modal Common Ground
• "Show me the cup": Reference with Continuous Representations