Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network
Proceedings of the 23rd International Conference on Artificial Neural Networks (ICANN2013),
Editors: Valeri Mladenov and Petia Koprinkova-Hristova and Günther Palm and Alessandro E.P. Villa and Bruno Apolloni and Nicola Kasabov,
Volume 8131,
pages 216--223,
doi: 10.1007/978-3-642-40728-4_27
- Sep 2013
Associated documents :
How the human brain understands natural language and
what we can learn for intelligent systems is open research. Recently, researchers claimed that language is embodied in most if not all sensory
and sensorimotor modalities and that the brains architecture favours
the emergence of language. In this paper we investigate the characteristics of such an architecture and propose a model based on the Multiple
Timescale Recurrent Neural Network, extended by embodied visual perception. We show that such an architecture can learn the meaning of
utterances with respect to visual perception and that it can produce
verbal utterances that correctly describe previously unknown scenes.
@InProceedings{HWW13,
author = {Heinrich, Stefan and Weber, Cornelius and Wermter, Stefan},
title = {Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network},
booktitle = {Proceedings of the 23rd International Conference on Artificial Neural Networks (ICANN2013)},
editors = {Valeri Mladenov and Petia Koprinkova-Hristova and Günther Palm and Alessandro E.P. Villa and Bruno Apolloni and Nicola Kasabov},
number = {},
volume = {8131},
pages = {216--223},
year = {2013},
month = {Sep},
publisher = {Springer Heidelberg},
doi = {10.1007/978-3-642-40728-4_27},
}