Robots Learning to Say “No”

“No” is one of the first ten words used by children and embodies the first form of linguistic negation. Despite its early occurrence, the details of its acquisition remain largely unknown. The circumstance that “no” cannot be construed as a label for perceptible objects or events puts it outside the scope of most modern accounts of language acquisition. Moreover, most symbol grounding architectures will struggle to ground the word due to its non-referential character. The presented work extends symbol grounding to encompass affect and motivation. In a study involving the child-like robot iCub, we attempt to illuminate the acquisition process of negation words. The robot is deployed in speech-wise unconstrained interaction with participants acting as its language teachers. The results corroborate the hypothesis that affect or volition plays a pivotal role in the acquisition process. Negation words are prosodically salient within prohibitive utterances and negative intent interpretations such that they can be easily isolated from the teacher’s speech signal. These words subsequently may be grounded in negative affective states. However, observations of the nature of prohibition and the temporal relationships between its linguistic and extra-linguistic components raise questions over the suitability of Hebbian-type algorithms for certain types of language grounding.

[1]  J. Austin How to do things with words , 1962 .

[2]  R. Spitz No and Yes: On the Genesis of Human Communication , 1966 .

[3]  John R. Searle,et al.  Speech Acts: An Essay in the Philosophy of Language , 1970 .

[4]  J. Ryan,et al.  Early language development: Towards a communicational analysis. , 1974 .

[5]  E. Newport MOTHERESE: THE SPEECH OF MOTHERS TO YOUNG CHILDREN. , 1975 .

[6]  R. Pea The development of negation in early child language , 1978 .

[7]  M. Bowerman The 'no negative evidence' problem: How do children avoid constructing an overly general grammar? , 1988 .

[8]  Alison Gopnik,et al.  Three types of early word: the emergence of social words, names and cognitive-relational words in the one-word stage and their relation to cognitive development , 1988 .

[9]  G. Jefferson Preliminary notes on a possible metric which provides for a 'standard maximum' silence of approximately one second in conversation. , 1989 .

[10]  Stevan Harnad,et al.  Symbol grounding problem , 1990, Scholarpedia.

[11]  E. Rosch,et al.  The Embodied Mind: Cognitive Science and Human Experience , 1993 .

[12]  J. Cacioppo,et al.  Emotional Contagion , 1993 .

[13]  Brian Richards,et al.  Input and interaction in language acquisition: Types of language learner , 1994 .

[14]  M. Tomasello,et al.  Variability in early communicative development. , 1994, Monographs of the Society for Research in Child Development.

[15]  David W. Aha,et al.  Lazy Learning , 1997, Springer Netherlands.

[16]  Why is a pomegranate an apple? The role of shape, taxonomic relatedness, and prior lexical knowledge in children's overextensions of apple and dog* , 1998 .

[17]  Robin Wooffitt,et al.  Conversation Analysis: Principles, Practices and Applications , 1998 .

[18]  L. Barsalou,et al.  Whither structured representation? , 1999, Behavioral and Brain Sciences.

[19]  M. Tomasello,et al.  Young children's overgeneralizations with fixed transitivity verbs. , 1999, Child development.

[20]  Kathy Hirsh-Pasek,et al.  I. What Does it Take to Learn a Word , 2000 .

[21]  Jeffrey Mark Siskind,et al.  Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic , 1999, J. Artif. Intell. Res..

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

[23]  Luc Steels,et al.  Shared grounding of event descriptions by autonomous robots , 2003, Robotics Auton. Syst..

[24]  Peter Ford Dominey,et al.  Learning to talk about events from narrated video in a construction grammar framework , 2005, Artif. Intell..

[25]  M. Tomasello Constructing a Language , 2005 .

[26]  Jun Tani,et al.  Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes , 2005, Adapt. Behav..

[27]  Deb Roy,et al.  Semiotic schemas: A framework for grounding language in action and perception , 2005, Artif. Intell..

[28]  Linda B. Smith,et al.  Hypothesis Testing and Associative Learning in Cross-Situational Word Learning: Are They One and the Same? , 2007 .

[29]  Giulio Sandini,et al.  The iCub humanoid robot: an open platform for research in embodied cognition , 2008, PerMIS.

[30]  Alexandre Bernardino,et al.  Multimodal saliency-based bottom-up attention a framework for the humanoid robot iCub , 2008, 2008 IEEE International Conference on Robotics and Automation.

[31]  Walter Daelemans,et al.  Memory-Based Language Processing , 2009, Studies in natural language processing.

[32]  Y. Niv Reinforcement learning in the brain , 2009 .

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

[34]  Angelo Cangelosi,et al.  Grounding language in action and perception: from cognitive agents to humanoid robots. , 2010, Physics of life reviews.

[35]  G. Vigliocco,et al.  The representation of abstract words: why emotion matters. , 2011, Journal of experimental psychology. General.

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

[37]  Chrystopher L. Nehaniv,et al.  The acquisition of word semantics by a humanoid robot via interaction with a human tutor , 2011 .

[38]  Chrystopher L. Nehaniv,et al.  Robot acquisition of lexical meaning - moving towards the two-word stage , 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[39]  Frank Foerster Robots that Say ’No’: Acquisition of Linguistic Behaviour in Interaction Games with Humans , 2013 .

[40]  Frank Broz,et al.  Interaction and experience in enactive intelligence and humanoid robotics , 2013, 2013 IEEE Symposium on Artificial Life (ALife).

[41]  Jamil Zaki,et al.  Affective cognition: Exploring lay theories of emotion , 2015, Cognition.

[42]  Stefano Nolfi,et al.  Embodied Language Learning and Cognitive Bootstrapping: Methods and Design Principles , 2016 .

[43]  R. Mccall,et al.  The Genetic and Environmental Origins of Learning Abilities and Disabilities in the Early School , 2007, Monographs of the Society for Research in Child Development.

[44]  Casey Redd Kennington,et al.  Symbol, Conversational, and Societal Grounding with a Toy Robot , 2017, ArXiv.

[45]  Geoffrey I. Webb Lazy Learning , 2010, Encyclopedia of Machine Learning.

[46]  Angelo Cangelosi,et al.  Making sense of words: a robotic model for language abstraction , 2016, Autonomous Robots.

[47]  Angelo Cangelosi,et al.  Mapping Language to Vision in a Real-World Robotic Scenario , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[48]  Frank Foerster Coding Scheme for Negative Utterances , 2018 .

[49]  Chrystopher L. Nehaniv,et al.  Robots That Say “No” Affective Symbol Grounding and the Case of Intent Interpretations , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[50]  Jamil Zaki,et al.  Computational Models of Emotion Inference in Theory of Mind: A Review and Roadmap , 2018, Top. Cogn. Sci..