Advertisement

Implementation of Biases Observed in Children’s Language Development into Agents

  • Ryo Taguchi
  • Masashi Kimura
  • Shuji Shinohara
  • Kouichi Katsurada
  • Tsuneo Nitta
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4211)

Abstract

This paper describes efficient word meaning acquisition for infant agents (IAs) based on learning biases that are observed in children’s language development. An IA acquires word meanings through learning the relations among visual features of objects and acoustic features of human speech. In this task, the IA has to find out which visual features are indicated by the speech. Previous works introduced stochastic approaches to do this, however, such approaches need many examples to achieve high accuracy. In this paper, firstly, we propose a word meaning acquisition method for the IA based on an Online-EM algorithm without learning biases. Then, we implement two types of biases into it to accelerate the word meaning acquisition. Experimental results show that the proposed method with biases can efficiently acquire word meanings.

Keywords

Visual Feature Word Meaning Target Attribute Human Speech Unknown Word 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Harnad, S.: The symbol grounding problem. Physica D 42, 335–346 (1990)CrossRefGoogle Scholar
  2. 2.
    Pfeifer, R., Scheier, C.: Understanding Intelligence. The MIT Press, Cambridge (1999)Google Scholar
  3. 3.
    Akaho, S., et al.: Concept acquisition from multiple information sources by the EM algorithm. IEICE Trans. J80-A(9), 1546–1553 (1997)Google Scholar
  4. 4.
    Roy, D.: Integration of speech and vision using mutual information. In: Proc. ICASSP, vol. 4, pp. 2369–2372 (2000)Google Scholar
  5. 5.
    Iwahashi, N.: Language acquisition through a human-robot interface by combining speech, visual, and behavioral information. Information Sciences 156, 109–121 (2003)CrossRefGoogle Scholar
  6. 6.
    Otsu, N., Kurita, T.: A new scheme for practical, flexible and intelligent vision systems. In: Lee, S.-W., Nakano, Y. (eds.) DAS 1998. LNCS, vol. 1655. Springer, Heidelberg (1999)Google Scholar
  7. 7.
    Sato, M., Ishii, S.: On-line EM algorithm for the normalized Gaussian network. Neural Computation 12(2), 407–432 (2000)CrossRefGoogle Scholar
  8. 8.
    Markman, E.M.: Categorization and naming in children. MIT Press, Cambridge (1989)Google Scholar
  9. 9.
    Landau, B., et al.: The importance of shape in early lexical learning. Cognitive Development 3, 299–321 (1988)CrossRefGoogle Scholar
  10. 10.
    Clark, E.: The principle of contrast: A constraint on language acquisition. In: MacWhinney, B. (ed.) Mechanisms of language acquisition, pp. 1–33. Lawrence Erlbaum, Hillsdale (1987)Google Scholar
  11. 11.
    Imai, M., Haryu, E.: The nature of word learning biases: From a cross linguistic perspective. In: Hall, D.G., Waxman, S. (eds.) Weaving a lexicon, pp. 411–444. MIT Press, Cambridge (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ryo Taguchi
    • 1
  • Masashi Kimura
    • 1
  • Shuji Shinohara
    • 1
  • Kouichi Katsurada
    • 1
  • Tsuneo Nitta
    • 1
  1. 1.Graduate School of Engineering, Toyohashi University of TechnologyToyohashi-cityJapan

Personalised recommendations