@inproceedings{df0ae69243f847b0bb8dc971e31e5b17,
title = "Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network",
abstract = "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 brain{\textquoteright}s 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.",
keywords = "Embodied Language, MTRNN, Language Acquisition",
author = "Stefan Heinrich and Cornelius Weber and Stefan Wermter",
year = "2013",
month = sep,
day = "1",
doi = "10.1007/978-3-642-40728-4_27",
language = "English",
volume = "8131",
series = "Lecture Notes in Computer Science",
pages = "216--223",
editor = "Valeri Mladenov and Petia Koprinkova-Hristova and G{\"u}nther Palm and Villa, {Alessandro E.P.} and Bruno Apolloni and Nicola Kasabov",
booktitle = "Proceedings of the 23rd International Conference on Artificial Neural Networks (ICANN2013)",
publisher = "Springer",
address = "Germany",
}