A computational model of adults' performance in naming objects using cross-situational learning

People learn the meaning of words in ambiguous contexts with many possible words for any referent and many referents for any word. Cross-situational learning is an approach to solve this word-to-world mapping problem based on the idea that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Here we investigate the performance of a simplified variant of the general-purpose Neural Modeling Fields (NMF) categorization mechanism to infer the correct word-referent mapping in a cross-situational learning scenario that simulates experiments with adult subjects. We study two learning situations: the batch-mode learning in which the processing of data requires the memorization of all training examples, and the online learning in which the data processing occurs concomitantly with the exhibition of the examples. A training example consists of a picture of a number of objects accompanied by the utterance of the same number of words. We show that the equations derived to describe the batch-mode learning situation can also be applied to the more realistic online learning situation The resulting online algorithm yields predictions which are both qualitatively and quantitatively in agreement with the experimental results.

[1]  P. Bloom.  How Children Learn the Meaning of Words and How LSA Does It ( Too ) , 2005 .

[2]  Leonid I. Perlovsky,et al.  Language and emotions: Emotional Sapir-Whorf hypothesis , 2009, Neural Networks.

[3]  W. Strange.  Evolution of language. , 1984, JAMA.

[4]  Leonid I. Perlovsky,et al.  Evolving Compositionality in Evolutionary Language Games , 2007, IEEE Transactions on Evolutionary Computation.

[5]  James R. Hurford,et al.  Biological evolution of the Saussurean sign as a component of the language acquisition device , 1989 .

[6]  Chen Yu,et al.  Statistical Cross-Situational Learning to Build Word-to-World Mappings , 2006 .

[7]  Andrew D. M. Smith,et al.  Semantic Generalisation and the Inference of Meaning , 2003, ECAL.

[8]  Angelo Cangelosi,et al.  Evolution of communication and language using signals, symbols, and words , 2001, IEEE Trans. Evol. Comput..

[9]  Angelo Cangelosi,et al.  Language and Cognition Integration Through Modeling Field Theory: Category Formation for Symbol Grounding , 2006, ICANN.

[10]  E. Spelke,et al.  Perception of partly occluded objects in infancy , 1983, Cognitive Psychology.

[11]  J. Mehler,et al.  LANGUAGE AND COGNITION , 1998 .

[12]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[13]  Leonid I. Perlovsky,et al.  A game theoretical approach to the evolution of structured communication codes , 2008, Theory in Biosciences.

[14]  A. Cangelosi,et al.  Symbol grounding and the symbolic theft hypothesis , 2002 .

[15]  Leonid I. Perlovsky,et al.  Meaning creation and communication in a community of agents , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[16]  Leonid I. Perlovsky,et al.  How language can help discrimination in the Neural Modelling Fields framework , 2008, Neural Networks.

[17]  M. Tomasello.  Perceiving intentions and learning words in the second year of life , 2000 .

[18]  Leonid Perlovsky,et al.  Neural Networks and Intellect: Using Model-Based Concepts , 2000, IEEE Transactions on Neural Networks.

[19]  J.F. Fontanari,et al.  Integrating Language and Cognition: A Cognitive Robotics Approach , 2007, IEEE Computational Intelligence Magazine.

[20]  Leonid I. Perlovsky,et al.  Integrated Emotions, Cognition, and Language , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[21]  J. Fontanari,et al.  Solvable null model for the distribution of word frequencies. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  Wesley E. Snyder,et al.  Optimization by Mean Field Annealing , 1988, NIPS.

[23]  Leonid I. Perlovsky,et al.  Cognitively Inspired Neural Network for Recognition of Situations , 2010, Int. J. Nat. Comput. Res..

[24]  Tony Belpaeme,et al.  A cross-situational learning algorithm for damping homonymy in the guessing game , 2006 .

[25]  José F. Fontanari.  Statistical analysis of discrimination games , 2006 .

[26]  Linda B. Smith,et al.  Infants rapidly learn word-referent mappings via cross-situational statistics , 2008, Cognition.

[27]  Angelo Cangelosi,et al.  2009 Special Issue: Cross-situational learning of object-word mapping using Neural Modeling Fields , 2009 .

[28]  J. Siskind.  A computational study of cross-situational techniques for learning word-to-meaning mappings , 1996, Cognition.

[29]  M. R. Manzini.  Learnability and Cognition , 1991 .

[30]  Ellen M. Markman,et al.  Constraints Children Place on Word Meanings , 1990, Cogn. Sci..

[31]  J. Elman,et al.  Learning Rediscovered , 1996, Science.

[32]  L. Gleitman.  The Structural Sources of Verb Meanings , 2020, Sentence First, Arguments Afterward.