From symbol grounding to socially shared embodied language knowledge

Tuci Elio

doi:10.3389/conf.fncom.2011.52.00025

Abstract

Much language-related research in cognitive robotics appeals to usage-based models of language as proposed in cognitive linguistics and developmental psychology [1, 2] that emphasise the significance of learning, embodiment and general cognitive development for human language acquisition. Over and above these issues, however, what takes centre stage in these theories are social-cognitive skills of “intention-reading” that are seen as “primary in the language acquisition process” [1] – and also as difficult to incorporate into computational models of language acquisition. The present paper addresses these concerns: we describe work in progress on a series of experiments that take steps towards closing the gap between ‘solipsistic’ symbol grounding in individual robotic agents and socially framed embodied language acquisition in learners that attend to common ground [3] with changing interlocutors.

Highlights

Much language-related research in cognitive robotics appeals to usage-based models of language as proposed in cognitive linguistics and developmental psychology [1, 2] that emphasise the significance of learning, embodiment and general cognitive development for human language acquisition
The present paper addresses these concerns: we describe work in progress on a series of experiments that take steps towards closing the gap between ‘solipsistic’ symbol grounding in individual robotic agents and socially framed embodied language acquisition in learners that attend to common ground [3] with changing interlocutors
Adnominal possessives are a linguistic universal [4] and among the first multiword constructions to emerge in early child speech [5]

Summary

INTRODUCTION

Much language-related research in cognitive robotics appeals to usage-based models of language as proposed in cognitive linguistics and developmental psychology [1, 2] that emphasise the significance of learning, embodiment and general cognitive development for human language acquisition. Over and above these issues, what takes centre stage in these theories are social-cognitive skills of “intention-reading” that are seen as “primary in the language acquisition process” [1] – and as difficult to incorporate into computational models of language acquisition. The present paper addresses these concerns: we describe work in progress on a series of experiments that take steps towards closing the gap between ‘solipsistic’ symbol grounding in individual robotic agents and socially framed embodied language acquisition in learners that attend to common ground [3] with changing interlocutors

Learning target and experimental design

General properties of the computational model

CONCLUSION