Co-Acquisition of Syntax and Semantics - An Investigation in Spatial Language

This paper reports recent progress on modeling the grounded co-acquisition of syntax and semantics of locative spatial language in developmental robots. We show how a learner robot can learn to produce and interpret spatial utterances in guided-learning interactions with a tutor robot (equipped with a system for producing English spatial phrases). The tutor guides the learning process by simplifying the challenges and complexity of utterances, gives feedback, and gradually increases the complexity of the language to be learnt. Our experiments show promising results towards long-term, incremental acquisition of natural language in a process of co-development of syntax and semantics.

[1]  Chrystopher L. Nehaniv,et al.  Towards using prosody to scaffold lexical meaning in robots , 2011, 2011 IEEE International Conference on Development and Learning (ICDL).

[2]  Penelope Brown.  Up, down, and across the land: landscape terms, place names, and spatial language in Tzeltal , 2008 .

[3]  Michael Spranger,et al.  Acquisition of Grammar in Autonomous Artificial Systems , 2010, ECAI.

[4]  Simon Pauw,et al.  The Emergence of Quantifiers , 2012 .

[5]  Luc Steels,et al.  Language games for autonomous robots , 2001 .

[6]  Reinhard Moratz,et al.  Group-based Spatial Reference in Linguistic Human-Robot Interaction , 2003 .

[7]  J. Tenenbaum,et al.  Probabilistic models of cognition: exploring representations and inductive biases , 2010, Trends in Cognitive Sciences.

[8]  Dieter Fox,et al.  Following directions using statistical machine translation , 2010, HRI 2010.

[9]  Michael Spranger,et al.  Grounded lexicon acquisition — Case studies in spatial language , 2013, 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[10]  Suzanne Stevenson,et al.  A Computational Model of Early Argument Structure Acquisition , 2008, Cogn. Sci..

[11]  Masaki Ogino,et al.  Cognitive Developmental Robotics: A Survey , 2009, IEEE Transactions on Autonomous Mental Development.

[12]  Terry Winograd,et al.  Procedures As A Representation For Data In A Computer Program For Understanding Natural Language , 1971 .

[13]  Luc Steels,et al.  The Grounded Colour Naming Game , 2009 .

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

[15]  S. Levinson.  Space in language and cognition: Explorations in cognitive diversity , 2003 .

[16]  Raymond J. Mooney,et al.  Learning to Interpret Natural Language Navigation Instructions from Observations , 2011, Proceedings of the AAAI Conference on Artificial Intelligence.

[17]  Luc Steels,et al.  Open-ended Procedural Semantics , 2012, Language Grounding in Robots.

[18]  Michael C. Frank,et al.  A Bayesian Framework for Cross-Situational Word-Learning , 2007, NIPS.

[19]  Chrystopher L. Nehaniv,et al.  A constructivist approach to robot language learning via simulated babbling and holophrase extraction , 2009, 2009 IEEE Symposium on Artificial Life.

[20]  Annette Herskovits,et al.  Language and spatial cognition , 1986 .

[21]  Jerome A. Feldman,et al.  Modeling Embodied Lexical Development , 1997 .

[22]  Soteria Svorou,et al.  The grammar of space , 1994 .

[23]  Nicholas Haddock,et al.  Computational models of incremental semantic interpretation , 1989 .

[24]  S. Levinson,et al.  'Uphill' and 'downhill' in Tzeltal , 1993 .

[25]  Stefanie Tellex,et al.  Learning perceptually grounded word meanings from unaligned parallel data , 2012, Machine Learning.

[26]  Gudula Retz-Schmidt,et al.  Various Views on Spatial Prepositions , 1988, AI Mag..

[27]  M. Pollack.  Journal of Artificial Intelligence Research: Preface , 2001 .

[28]  J. Siskind.  A computational study of cross-situational techniques for learning word-to-meaning mappings , 1996, Cognition.