Learning grounded semantics with word trees: Prepositions and pronouns

The authors present a method by which a robot can learn the meanings of words from unlabeled correct examples in context. The "word trees" method consists of reconstructing the speaker's decision process in choosing a word. The facts about an object and its relation to other objects that maximally reduce the uncertainty (entropy) of word choice become (he decision nodes of this tree. The conjunction of the choices leading to a word becomes its logical definition. Definitions thereby become only as complex as is necessary to distinguish words in the vocabulary, making the method appear to follow a heuristic that developmental psychologists call the "Principle of Contrast." Combined with a method for inferring word type and reference, the method produces semantics complete enough to produce or understand full sentences. The method was implemented on a robot with visual, auditory, and positional sensors, and succeeded in learning the differences between "I," "you," "he," "this," "that," "above," "below," and "near."

[1]  S. Heath.  Ways with Words: Language, Life and Work in Communities and Classrooms , 1983 .

[2]  Jeffrey Mark Siskind,et al.  Lexical Acquisition in the Presence of Noise and Homonymy , 1994, AAAI.

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

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

[5]  Stuart M. Shieber,et al.  Prolog and Natural-Language Analysis , 1987 .

[6]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[7]  David R. Dowty,et al.  Introduction to Montague semantics , 1980 .

[8]  C. Cairns,et al.  How Children Learn Language. , 1969 .

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

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

[11]  E. Markman,et al.  Children's use of mutual exclusivity to constrain the meanings of words , 1988, Cognitive Psychology.

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

[13]  Carl de Marcken,et al.  Unsupervised language acquisition , 1996, ArXiv.

[14]  Eve V. Clark,et al.  The principle of contrast: A constraint on language acquisition. , 1987 .

[15]  Siobhan Chapman.  Logic and Conversation , 2005 .

[16]  Jerome A. Feldman,et al.  When push comes to shove: a computational model of the role of motor control in the acquisition of action verbs , 1997 .

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

[18]  Terry Regier,et al.  The Human Semantic Potential: Spatial Language and Constrained Connectionism , 1996 .

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

[20]  Bodhi Priyantha,et al.  The Cricket indoor location system , 2005 .

[21]  Brian Scassellati,et al.  A Robot That Uses Existing Vocabulary to Infer Non-Visual Word Meanings from Observation , 2007, AAAI.