Enactivism and Robotic Language Acquisition: A Report from the Frontier
2. Theoretical Underpinnings and Methodological Choices
2.1. Robots Acquiring Language: Why and How?
2.2. Robots Acquiring Linguistic Negation: Why and How?
3.6. Affect or Volition
4. Discussion and Future Work
Conflicts of Interest
|NLP||Natural Language Processing|
|SDS||Spoken Dialogue Systems|
- Förster, F.; Saunders, J.; Nehaniv, C.L. Robots that Say ‘No’. Affective Symbol Grounding and the Case of Intent Interpretations. IEEE Trans. Cogn. Dev. Syst. 2017, 10, 530–544. [Google Scholar] [CrossRef]
- Förster, F.; Saunders, J.; Lehmann, H.; Nehaniv, C.L. Robots Learning to Say ‘No’: Prohibition and Rejective Mechanisms in Acquisition of Linguistic Negation. arXiv, 2018; arXiv:1810.11804. [Google Scholar]
- Nehaniv, C.L.; Förster, F.; Saunders, J.; Broz, F.; Antonova, E.; Köse, H.; Lyon, C.; Lehmann, H.; Sato, Y.; Dautenhahn, K. Interaction and experience in enactive intelligence and humanoid robotics. In Proceedings of the 2013 IEEE Symposium on Artificial Life (ALIFE), Singapore, 16–19 April 2013; pp. 148–155. [Google Scholar]
- de Jong, M.; Zhang, K.; Roth, A.M.; Rhodes, T.; Schmucker, R.; Zhou, C.; Ferreira, S.; Cartucho, J.; Veloso, M. Towards a Robust Interactive and Learning Social Robot. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, Stockholm, Sweden, 10–15 July 2018; pp. 883–891. [Google Scholar]
- Ward, N.G.; DeVault, D. Ten Challenges in Highly-Interactive Dialog System; Turn-Taking and Coordination in Human-Machine Interaction: Papers from the 2015 AAAI Spring Symposium; The AAAI Press: Palo Alto, CA, UAS, 2015. [Google Scholar]
- Porcheron, M.; Fischer, J.E.; Reeves, S.; Sharples, S. Voice Interfaces in Everyday Life. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, Montreal, QC, Canada, 21–26 April 2018. [Google Scholar]
- Harnad, S. The Symbol Grounding Problem. Physica D 1990, 42, 335–346. [Google Scholar] [CrossRef]
- Siskind, J.M. Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic. J. Artif. Intell. Res. 2001, 15, 31–90. [Google Scholar] [CrossRef]
- Sugita, Y.; Tani, J. Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes. Adapt. Behav. 2005, 13, 33–52. [Google Scholar] [CrossRef][Green Version]
- Saunders, J.; Nehaniv, C.L.; Lyon, C. The acquisition of word semantics by a humanoid robot via interaction with a human tutor. In New Frontiers in Human-Robot Interaction; Dautenhahn, K., Saunders, J., Eds.; John Benjamins Publishing Company: Amsterdam, The Netherlands, 2011; pp. 211–234. [Google Scholar]
- Saunders, J.; Lehmann, H.; Sato, Y.; Nehaniv, C.L. Towards Using Prosody to Scaffold Lexical Meaning in Robots. In Proceedings of the 2011 IEEE International Conference on Development and Learning (ICDL), Frankfurt am Main, Germany, 24–27 August 2011. [Google Scholar]
- Saunders, J.; Lehmann, H.; Förster, F.; Nehaniv, C.L. Robot Acquisition of Lexical Meaning—Moving Towards the Two-word Stage. In Proceedings of the 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL), San Diego, CA, USA, 7–9 November 2012. [Google Scholar]
- Kennington, C.; Plane, S. Symbol, Conversational, and Societal Grounding with a Toy Robot. arXiv, 2017; arXiv:1709.10486. [Google Scholar]
- Tomasello, M. Constructing a Language; Harvard University Press: Cambridge, MA, USA, 2009. [Google Scholar]
- Broz, F.; Nehaniv, C.L.; Belpaeme, T.; Bisio, A.; Dautenhahn, K.; Fadiga, L.; Ferrauto, T.; Fischer, K.; Förster, F.; Gigliotta, O.; et al. The ITALK Project: A Developmental Robotics Approach to the Study of Individual, Social, and Linguistic Learning. Top. Cogn. Sci. 2014, 6, 534–544. [Google Scholar] [CrossRef] [PubMed][Green Version]
- Fenson, L.; Dale, P.S.; Reznick, J.S.; Bates, E.; Thal, D.J.; Pethick, S.J. Variability in Early Communicative Development. Monogr. Soc. Res. Child Dev. 1994, 59, i-185. [Google Scholar] [CrossRef]
- Pea, R. The Development Of Negation In Early Child Language. In The Social Foundations of Language and Thought: Essays in Honor of Jerome S. Bruner; Olson, D., Ed.; W.W. Norton: New York, NY, USA, 1980; pp. 156–186. [Google Scholar]
- Metta, G.; Sandini, G.; Vernon, D.; Natale, L.; Nori, F. The iCub humanoid robot: An open platform for research in embodied cognition. In Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems, Gaithersburg, MD, USA, 19–21 August 2008; pp. 50–56. [Google Scholar]
- Förster, F. Robots That Say ‘No’: Acquisition of Linguistic Behaviour in Interaction Games with Humans. Ph.D. Thesis, University of Hertfordshire, Hertfordshire, UK, 2013. [Google Scholar]
- Ryan, J. Early language development: Towards a communicational analysis. In The Integration of a Child into a Social World; Richards, M.P.M., Ed.; Cambridge University Press: Cambridge, UK, 1974. [Google Scholar]
- Spitz, R.A. No and Yes: On the Genesis of Human Communication; International Universities Press: New York, NY, USA, 1957. [Google Scholar]
- De Jaegher, H.; Di Paolo, E.A. Participatory sense-making. Phenomenol. Cogn. Sci. 2007, 6, 485–507. [Google Scholar] [CrossRef]
- Varela, F.J.; Thompson, E.; Rosch, E. The Embodied Mind: Cognitive Science and Human Experience; MIT Press: Cambridge, MA, USA, 1991. [Google Scholar]
- Wilson, R.A.; Foglia, L. Embodied Cognition. In The Stanford Encyclopedia of Philosophy; Zalta, E.N., Ed.; Spring 2017 ed.; Metaphysics Research Lab, Stanford University: Stanford, CA, USA, 2017. [Google Scholar]
- Varela, F.J.; Thompson, E.; Rosch, E. The Embodied Mind: Cognitive Science and Human Experience—Revised Edition; MIT Press: Cambridge, MA, USA, 2016. [Google Scholar]
- Di Paolo, E.A.; Rohde, M.; De Jaegher, H. Horizons for the Enactive Mind: Values, Social Interaction, and Play. In Enaction: Toward a New Paradigm for Cognitive Science; Steward, J., Gapenne, O., Di Paolo, E.A., Eds.; MIT Press: Cambridge, MA, USA, 2010. [Google Scholar]
- O’Regan, J.K. Why Red Doesn’t Sound Like a Bell: Understanding the Feel of Consciousness; Oxford University Press: Oxford, UK, 2011. [Google Scholar]
- Hutto, D.D.; Myin, E. Radicalizing Enactivism: Basic Minds without Content; MIT Press: Cambridge, MA, USA, 2012. [Google Scholar]
- Dumas, G.; Lefebvre, A.; Zhang, M.; Tognoli, E.; Kelso, J.S. The Human Dynamic Clamp: A Probe for Coordination Across Neural, Behavioral, and Social Scales. In Complexity and Synergetics; Müller, S., Plath, P., Radons, G., Fuchs, A., Eds.; Springer: Cham, Switzerland, 2017. [Google Scholar]
- Sacks, H.; Schegloff, E.A.; Jefferson, G. A Simplest Systematics for the Organization of Turn-Taking for Conversation. Language 1974, 50, 696–735. [Google Scholar] [CrossRef]
- Jefferson, G. Preliminary notes on a possible metric which provides for a “standard maximum” silence of approximately one second in conversation. In Conversation: An Interdisciplinary Perspective; Roger, D., Bull, P., Eds.; Multilingual Matters: Clevedon, UK, 1989; Chapter 8; pp. 166–196. [Google Scholar]
- Aha, D.W. (Ed.) Lazy Learning; Springer-Science+Business Media: Dordrecht, The Netherlands, 1997. [Google Scholar]
There are still many occasions where spoken dialogue systems (SDS) fail dramatically. In robotics, the on-board speech recognition is often times sub-optimal due to the presence of noise or due to a limited speech corpus (cf. ). However, even assuming perfect speech recognition, a dialogue system may have too narrow a focus in terms of the application area that the designers envisioned (cf. Ward et al. for a wish-list for future dialogue systems ). Moreover, our understanding and modelling of conversational capabilities seem to lag far behind developments in speech recognition (cf.  for some revealing transcripts of ‘conversations’ between humans and voice interfaces).
While some symbol grounding architectures ground linguistic entities directly in sensorimotor data, others may link them to abstractions thereof (‘concepts’). In particular, logical-type architectures similar to the one developed by Siskind  involve multiple layers of explicit ‘data abstraction’. In these cases, the established link is not a direct one. The derived concepts, however, are typically causally linked to the agent’s sensorimotor context, such that a link between ‘word’ and ‘world’ can be postulated and just requires the analyst’s willingness to go through several abstraction layers.
A detailed analysis of potential confusions of coders with respect to negation words that occurred in our studies and the reasons behind these confusions are provided in .
© 2019 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Förster, F. Enactivism and Robotic Language Acquisition: A Report from the Frontier. Philosophies 2019, 4, 11. https://doi.org/10.3390/philosophies4010011
Förster F. Enactivism and Robotic Language Acquisition: A Report from the Frontier. Philosophies. 2019; 4(1):11. https://doi.org/10.3390/philosophies4010011Chicago/Turabian Style
Förster, Frank. 2019. "Enactivism and Robotic Language Acquisition: A Report from the Frontier" Philosophies 4, no. 1: 11. https://doi.org/10.3390/philosophies4010011