Related links

Authoritative: http://dx.doi.org/10.1007/11880172_8   (Publisher's PDF... likely be available here.)

Web search: Google Web Search   ::   Google Scholar

Within this site: References (11)

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.

@inproceedings{taguchi06children,
  author={Ryo Taguchi and Masashi Kimura and Shuji Shinohara and Kouichi Katsurada and Tsuneo Nitta},
  title={Implementation of Biases Observed in Children's Language Development into Agents},
  year={2006},
  pages={89-99},
  editor={P. Vogt and et al.},
  publisher={Springer},
  booktitle={Symbol Grounding and Beyond: Proceedings of the Third International Workshop on the Emergence and Evolution of Linguistic Communication},
  doi={10.1007/11880172_8},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/taguchi06children.html}
}