Language Bootstrapping: Learning Word Meanings From Perception–Action Association

  title={Language Bootstrapping: Learning Word Meanings From Perception–Action Association},
  author={Giampiero Salvi and L. Montesano and A. Bernardino and J. Santos-Victor},
  journal={IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)},
  • Giampiero Salvi, L. Montesano, +1 author J. Santos-Victor
  • Published 2012
  • Computer Science, Medicine, Mathematics
  • IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • We address the problem of bootstrapping language acquisition for an artificial system similarly to what is observed in experiments with human infants. Our method works by associating meanings to words in manipulation tasks, as a robot interacts with objects and listens to verbal descriptions of the interactions. The model is based on an affordance network, i.e., a mapping between robot actions, robot perceptions, and the perceived effects of these actions upon objects. We extend the affordance… CONTINUE READING
    Active Learning for Teaching a Robot Grounded Relational Symbols
    • 68
    • PDF
    Affordances in Psychology, Neuroscience, and Robotics: A Survey
    • 83
    • PDF
    Robot anticipation of human intentions through continuous gesture recognition
    • 22
    • PDF


    Publications referenced by this paper.
    The Ecological Approach to Visual Perception
    • 15,397
    • PDF
    Latent Dirichlet Allocation
    • 24,105
    • PDF
    A computational study of cross-situational techniques for learning word-to-meaning mappings
    • 514
    • PDF
    Causality: Models, Reasoning, and Inference
    • 9,523
    • PDF
    A unified model of early word learning: Integrating statistical and social cues
    • 194
    • PDF
    A Tutorial on Learning with Bayesian Networks
    • 1,506
    • PDF
    How the body shapes the way we think - a new view on intelligence
    • 640
    • PDF