DocumentCode :
635552
Title :
Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model
Author :
Ogata, Takaaki ; Okuno, Hiroshi G.
Author_Institution :
Sch. of Fundamental Sci. & Eng., Waseda Univ., Tokyo, Japan
fYear :
2013
fDate :
16-19 April 2013
Firstpage :
89
Lastpage :
95
Abstract :
This paper proposes an approach for robots to ac-quire language grounding in their robot´s sensory-motor flow using neuro-dynamical models. We trained our neuro-dynamical model over a set of sentences represented as sequences of characters. For the integrated recognition, we introduced a cognitive hypothesis for integrated recognition where a human´s brain separately processed the “structure” and “contents” of a sentence. Our model was trained with the spelling of words and their semantic role emerged in the first model. As a result of binding the model with sensory-motion patterns, we confirmed that it could associate proper word spellings with a sensory-motor flows and a semantic roles, even if an observed flow had not been learned.
Keywords :
human-robot interaction; natural language interfaces; natural language processing; neural nets; speech processing; cognitive hypothesis; hierarchal structure; human brain; integrated recognition; language grounding; neurodynamical models; robot sensory motor flow; semantic roles; sensory motion patterns; word spellings; Brain modeling; Grounding; Hidden Markov models; Neurons; Pragmatics; Robot sensing systems; behaviors; language grammer; neuro-dynamical systems; symbol grounding; word contents;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotic Intelligence In Informationally Structured Space (RiiSS), 2013 IEEE Workshop on
Conference_Location :
Singapore
Type :
conf
DOI :
10.1109/RiiSS.2013.6607934
Filename :
6607934
Link To Document :
بازگشت