Abstract
Meanings of language expressions are constructed not only from words grounded in real-world matters, but also from words such as “not” that participate in the construction by working as logical operators. This study proposes a connectionist method for learning and internally representing functions that deal with both of these word groups, and grounding sentences constructed from them in corresponding behaviors just by experiencing raw sequential data of an imposed task. In the experiment, a robot implemented with a recurrent neural network is required to ground imperative positive and negative sentences given as a sequence of words in corresponding goal-oriented behavior. Analysis of the internal representations reveals that the network fulfilled the requirement by extracting XOR problems implicitly included in the target sequences and solving them by learning to represent the logical operations in its nonlinear dynamics in a self-organizing manner.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cangelosi, A.: The sensorimotor bases of linguistic structure: experiments with grounded adaptive agents. In: Schaal, S., et al. (eds.) Proceedings of the Eighth International Conference on the Simulation of Adaptive Behaviour: From Animals to Animats, vol. 8, pp. 487–496. MIT Press, Cambridge (2004)
Sugita, Y., Tani, J.: Learning semantic combinatoriality from the interaction between linguistic and behavioral processes. Adapt. Behav. 13(1), 33–52 (2005)
Arie, H., Endo, T., Jeong, S., Lee, M., Sugano, S., Tani, J.: Integrative learning between language and action: a neuro-robotics experiment. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part II. LNCS, vol. 6353, pp. 256–265. Springer, Heidelberg (2010)
Tuci, E., Ferrauto, T., Zeschel, A., Massera, G., Nolfi, S.: An experiment on behavior generalization and the emergence of linguistic compositionality in evolving robots. IEEE Trans. Auton. Ment. Dev. 3(2), 176–189 (2011)
Stramandinoli, F., Marocco, D., Cangelosi, A.: The grounding of higher order concepts in action and language: a cognitive robotics model. Neural Netw. 32, 165–173 (2012)
Harnad, S.: The symbol grounding problem. Physica D 42(1–3), 335–346 (1990)
Partee, B.H.: Compositionality in Formal Semantics. Blackwell Publishers, Oxford (2004). Selected papers by Barbara H. Partee
Yamashita, Y., Tani, J.: Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS computational biology 4(11), e1000220 (2008)
Yamada, T., Murata, S., Arie, H., Ogata, T.: Attractor representations of language-behavior structure in a recurrent neural network for human-robot interaction. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2015), pp. 4179–4184 (2015)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, pp. 318–362. MIT Press, Cambridge (1986)
Acknowledgments
This work was supported by a Grant-in-Aid for Scientific Research on Innovative Areas “Constructive Developmental Science” (24119003), CREST, JST, and a Grant-in-Aid for Young Scientists (B) (26870649).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Yamada, T., Murata, S., Arie, H., Ogata, T. (2016). Dynamical Linking of Positive and Negative Sentences to Goal-Oriented Robot Behavior by Hierarchical RNN. In: Villa, A., Masulli, P., Pons Rivero, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2016. ICANN 2016. Lecture Notes in Computer Science(), vol 9886. Springer, Cham. https://doi.org/10.1007/978-3-319-44778-0_40
Download citation
DOI: https://doi.org/10.1007/978-3-319-44778-0_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44777-3
Online ISBN: 978-3-319-44778-0
eBook Packages: Computer ScienceComputer Science (R0)