Experiments with Single-class Support Vector Data Descriptions as a Tool for Vocabulary Grounding

Aneesh Chauhan, Luís Seabra Lopes

2010

Abstract

This paper explores support vectors as a tool for vocabulary acquisition in robots. The intention is to investigate the language grounding process at the single-word stage. A social language grounding scenario is designed, where a robotic agent is taught the names of the objects by a human instructor. The agent grounds the names of these objects by associating them with their respective sensor-based category descriptions. A system for grounding vocabulary should be incremental, adaptive and support gradual evolution. A novel learning model based on single-class support vector data descriptions (SVDD), which conforms to these requirements, is presented. For robustness and flexibility, a kernel based implementation of support vectors was realized. For this purpose, a sigmoid kernel using histogram pyramid matching has been developed. The support vectors are trained based on an original approach using genetic algorithms. The model is tested over a series of semi-automated experiments and the results are reported.

References

  1. Barsalou, L. 1999. Perceptual symbol systems. Behavioral and Brain Sciences, 22(4): 577-609.
  2. Bloom, P. 2000. How Children Learn the Meanings of Words. MIT Press, Cambridge, MA.
  3. Cowley, S. J. 2007. Distributed language: Biomechanics, functions and the origins of talk. In Lyon, Nehaniv & Cangelosi (eds), Emergence of communication and language, 105-127.
  4. Gold, K.; Doniec, M.; Christopher, C.; and Scassellati, B. 2009. Robotic Vocabulary Building Using Extension Inference and Implicit Contrast. Artificial Intelligence 173(1):145-166.
  5. Harnad, S. 1990. The symbol grounding problem. Physica D, 42:335-346.
  6. Grauman, K.; and Darrell, T. 2007:The Pyramid Match Kernel: Efficient Learning with Sets of Features. Journal of Machine Learning Research (JMLR), 8 (Apr): 725-760.
  7. Levinson, S. E.; Squire, K.; Lin, R. S.; and McClain, M. 2005. Automatic language acquisition by an autonomous robot, Proc. of AAAI Spring Symposium on Developmental Robotics.
  8. Loreto, V.; and Steels, L. 2008. Social dynamics: Emergence of language. Nature Physics, 3:758-760
  9. Love, N. 2004. Cognition and the language myth. Language Sciences, 26:525-544.
  10. Markman, E.S. (1989) Categorization and naming in children. Cambridge, MA: MIT Press.
  11. Platt, J. 1998. Sequential minimal optimization: A fast algorithm for training support vector machines. Microsoft Research Technical Report MSR-TR-98-14.
  12. Roy, D.; and Pentland, A. 2002. Learning words from sights and sounds: A computational model. Cognitive Science, 26:113-146.
  13. Seabra Lopes, L.; and Chauhan, A. 2007. How many Words can my Robot learn? An Approach and Experiments with One-Class Learning. Interaction Studies, 8(1):53-81.
  14. Seabra Lopes, L.; and Chauhan, A. 2008. Open-ended category learning for language acquisition. Connection Science, 20(4):277-297.
  15. Skocaj, D.; Berginc, G.; Ridge, B.; Štimec, B.; Jogan, M.; Vanek, O.; Leonardis, A.; Hutter, M.; and Hewes, N. 2007. A system for continuous learning of visual concepts,” In International Conference on Computer Vision Systems ICVS 2007, Bielefeld, Germany.
  16. Steels, L. 2007. The symbol grounding problem is solved, so what's next? In De Vega, M. and G. Glennberg and G. Graesser (eds), Symbols, embodiment and meaning. Academic Press, New Haven.
  17. Steels, L.; and Kaplan, F. 2002. AIBO's first words: The social learning of language and meaning. Evolution of Communication, 4(1):3-32.
  18. Tavakkoli, A.; Nicolescu, M.; Bebis, G.; and Nicolescu, M. 2008. A support vector data description approach for background modeling in videos with quasi-stationary backgrounds", International Journal of Artificial Intelligence Tools, 17(4):635-658.
  19. Tax, D. M. J. 2001. One Class Classification. PhD Thesis, Delft University of Technology
Download


Paper Citation


in Harvard Style

Chauhan A. and Lopes L. (2010). Experiments with Single-class Support Vector Data Descriptions as a Tool for Vocabulary Grounding . In Proceedings of the 7th International Workshop on Natural Language Processing and Cognitive Science - Volume 1: NLPCS, (ICEIS 2010) ISBN 978-989-8425-13-3, pages 70-78. DOI: 10.5220/0003028000700078


in Bibtex Style

@conference{nlpcs10,
author={Aneesh Chauhan and Luís Seabra Lopes},
title={Experiments with Single-class Support Vector Data Descriptions as a Tool for Vocabulary Grounding},
booktitle={Proceedings of the 7th International Workshop on Natural Language Processing and Cognitive Science - Volume 1: NLPCS, (ICEIS 2010)},
year={2010},
pages={70-78},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003028000700078},
isbn={978-989-8425-13-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Workshop on Natural Language Processing and Cognitive Science - Volume 1: NLPCS, (ICEIS 2010)
TI - Experiments with Single-class Support Vector Data Descriptions as a Tool for Vocabulary Grounding
SN - 978-989-8425-13-3
AU - Chauhan A.
AU - Lopes L.
PY - 2010
SP - 70
EP - 78
DO - 10.5220/0003028000700078