A probabilistic approach to learning a visually grounded language model through human-robot interaction

IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings

Volumn , Issue , 2010, Pages 790-796

  Dindo, Haris ^a   Zambuto, Daniele ^a  

^a UNIVERSITY OF PALERMO   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

COGNITIVE ACTIVITIES; COGNITIVE SCIENCE; HUMAN -ROBOT INTERACTIONS; HUMANOID ROBOT; HUMANOID ROBOTICS; MOTOR SKILLS; MULTI-INSTANCE LEARNING; NATURAL LANGUAGES; PROBABILISTIC APPROACHES; PROBABILISTIC MODELS; REAL OBJECTS; ROBOTIC PLATFORMS; RUDIMENTARY FORMS; SPOKEN WORDS; VISUALLY-GROUNDED LANGUAGE;

ANTHROPOMORPHIC ROBOTS; COMPUTATIONAL LINGUISTICS; HUMAN ROBOT INTERACTION; ROBOTICS;

INTELLIGENT ROBOTS;

EID: 78651510245     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IROS.2010.5654440     Document Type: Conference Paper

References (13)

1. D.A. Baldwin. Understanding the link between joint attention and language. Joint attention: Its origins and role in development, pages 131-158, 1995.
2. C.M. Bishop. Pattern recognition and machine learning. Springer New York, 2006.
3. P. Bloom. Intentionality and word learning. Trends in cognitive sciences, 1(1):9-12, 1997.
4. A. Cangelosi. Approaches to grounding symbols in perceptual and sensorimotor categories. Handbook of categorization in cognitive science, pages 719-737, 2005.
5. H. Dindo and D. Zambuto. Resolving ambiguities in a grounded human-robot interaction. Robot and Human Interactive Communication, 2009. RO-MAN 2009. The 18th IEEE International Symposium, pages 408-414, 2009.
6. C. Fisher, D.G. Hall, S. Rakowitz, and L. Gleitman. When it is better to receive than to give: Syntactic and conceptual constraints on vocabulary growth. The acquisition of the lexicon, pages 333-375, 1994.
7. K. Gold, M. Doniec, C. Crick, and B. Scassellati. Robotic vocabulary building using extension inference and implicit contrast. Artificial Intelligence, 173(1):145-166, 2009.
8. M. Heckmann, H. Brandl, J. Schmuedderich, X. Domont, B. Bolder, I. Mikhailova, H. Janssen, M. Gienger, A. Bendig, T. Rodemann, et al. Teaching a humanoid robot: Headset-free speech interaction for audio-visual association learning. The 18th IEEE International Symposium on Robot and Human Interactive Communication, 2009. RO-MAN 2009, pages 422-427, 2009.
9. G. Herzog and P. Wazinski. VIsual TRAnslator: Linking perceptions and natural language descriptions. Artificial Intelligence Review, 8(2):175-187, 1994.
10. O. Maron and T. Lozano-Pérez. A framework for multiple-instance learning. In Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems, pages 570-576. MIT Press Cambridge, MA, USA, 1998.
11. D. Roy. Learning visually grounded words and syntax for a scene description task. Computer Speech and Language, 16(3):353-385, 2002.
12. D. Roy. Grounding Words in Perception and Action: Insights from Computational Models. Trends in Cognitive Science, 9(8):389-396, 2005.
13. L. Steels and F. Kaplan. Bootstrapping grounded word semantics. Linguistic evolution through language acquisition, page 53, 2002.