Toward Fast Mapping for Robot Adjective Learning

Fast mapping is a phenomenon by which children learn the meanings of novel adjectives after a very small number of exposures when the new word is contrasted with a known word. The present study was a preliminary test of whether machine learners could use such contrasts in unconstrained speech to learn adjective meanings and categories. Six decision tree-based learning methods were evaluated that use contrasting examples in order to work toward an adjective fast-mapping system for machine learners. Subjects tended to compare objects using adjectives of the same category, implying that such contrasts may be a useful source of data about adjective meaning, though none of the learning algorithms showed strong advantages over any other.

[1]  J. Bennett.  Vision and Art: The Biology of Seeing , 2003 .

[2]  D. Roy.  Grounding spatial prepositions for video search , 2009 .

[3]  Anna Wierzbicka,et al.  What's in a Noun? (Or: How Do Nouns Differ in Meaning from Adjectives?) , 1986 .

[4]  Elissa L. Newport,et al.  Maturational Constraints on Language Learning , 1990, Cogn. Sci..

[5]  Kuntal Sengupta,et al.  A comparative study of different color spaces for foreground and shadow detection for traffic monitoring system , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[6]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[7]  C. Darwin,et al.  I.—A BIOGRAPHICAL SKETCH OF AN INFANT , 1877 .

[8]  Catherine L. Harris,et al.  The human semantic potential: Spatial language and constrained connectionism , 1997 .

[9]  P. Bloom.  How children learn the meanings of words , 2000 .

[10]  Allison Petrosino,et al.  Using information gain to build meaningful decision forests for multilabel classification , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[11]  F. Yates.  Contingency Tables Involving Small Numbers and the χ2 Test , 1934 .

[12]  Chen Yu,et al.  A multimodal learning interface for grounding spoken language in sensory perceptions , 2003, ICMI '03.

[13]  Richard L. Schiefelbusch,et al.  Cognition to language: Categories, word meanings, and training , 1980 .

[14]  Brian Scassellati,et al.  Robotic vocabulary building using extension inference and implicit contrast , 2009, Artificial Intelligence.

[15]  Brian Scassellati,et al.  Using sentence context and implicit contrast to learn sensor-grounded meanings for relational and deictic words: the twig system , 2008 .

[16]  Alex Pentland,et al.  Learning words from sights and sounds: a computational model , 2002, Cogn. Sci..

[17]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[18]  W. O'grady.  How children learn language , 2005 .

[19]  J. M. Anglin.  Vocabulary Development: A Morphological Analysis , 1994 .

[20]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[21]  Susan Carey,et al.  Acquiring a Single New Word , 1978 .

[22]  Charles Darwin,et al.  A biographical sketch of an infant , 1971, Annals of neurosciences.