How are you? How a Robot can Learn to Express its own Roboceptions

Abstract This work is framed on investigating how a robot can learn associations between linguistic elements, such as words or sentences, and its bodily perceptions, that we named “roboceptions”. We discuss the possibility of defining such a process of an association through the interaction with human beings. By interacting with a user, the robot can learn to ascribe a meaning to its roboceptions to express them in natural language. Such a process could then be used by the robot in a verbal interaction to detect some words recalling the previously experimented roboceptions. In this paper, we discuss a Dual-NMT approach to realize such an association. However, it requires adequate training corpus. For this reason, we consider two different phases towards the realization of the system, and we show the results of the first phase, comparing two approaches: one based on the Latent Semantic Analysis paradigm and one based on the Random Indexing methodology.

[1]  Steve R. Howell,et al.  A Model of Grounded Language Acquisition: Sensorimotor Features Improve Lexical and Grammatical Learning. , 2005 .

[2]  Giovanni Pilato,et al.  Robot Inner Perception Capability Through a Soft Somatosensory System , 2018, Int. J. Semantic Comput..

[3]  Tomoaki Nakamura,et al.  Online Algorithm for Robots to Learn Object Concepts and Language Model , 2017, IEEE Transactions on Cognitive and Developmental Systems.

[4]  Tomoaki Nakamura,et al.  Symbol emergence in robotics: a survey , 2015, Adv. Robotics.

[5]  Giovanni Pilato,et al.  TSVD as a Statistical Estimator in the Latent Semantic Analysis Paradigm , 2015, IEEE Transactions on Emerging Topics in Computing.

[6]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[7]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[8]  Angelo Cangelosi,et al.  Why Are There Developmental Stages in Language Learning? A Developmental Robotics Model of Language Development. , 2017, Cognitive science.

[9]  Domenico Parisi.  Robots with Language , 2010, Front. Neurorobot..

[10]  Angelo Cangelosi,et al.  Speech and Language in Humanoid Robots , 2018, Humanoid Robotics: A Reference.

[11]  Tie-Yan Liu,et al.  Dual Learning for Machine Translation , 2016, NIPS.

[12]  Jonas Langer,et al.  Language acquisition and conceptual development: The mosaic evolution of cognitive and linguistic ontogeny , 2001 .

[13]  Giovanni Pilato,et al.  Effectiveness of data-driven induction of semantic spaces and traditional classifiers for sarcasm detection , 2019, Natural Language Engineering.

[14]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[15]  G. Lakoff,et al.  Women, Fire, and Dangerous Things: What Categories Reveal about the Mind , 1988 .

[16]  Giovanni Pilato,et al.  Automatic Dictionary Creation by Sub-symbolic Encoding of Words , 2005, WIRN/NAIS.

[17]  Stefano Nolfi,et al.  The ITALK Project: A Developmental Robotics Approach to the Study of Individual, Social, and Linguistic Learning , 2014, Top. Cogn. Sci..

[18]  Pierre-Yves Oudeyer,et al.  MCA-NMF: Multimodal Concept Acquisition with Non-Negative Matrix Factorization , 2015, PloS one.