Show Reference: "Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network"

Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network In Artificial Neural Networks and Machine Learning – ICANN 2013, Vol. 8131 (2013), pp. 216-223, doi:10.1007/978-3-642-40728-4_27 by Stefan Heinrich, Cornelius Weber, Stefan Wermter edited by Valeri Mladenov, Petia Koprinkova-Hristova, Günther Palm, et al.
@incollection{heinrich-et-al-2013,
    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'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.},
    author = {Heinrich, Stefan and Weber, Cornelius and Wermter, Stefan},
    booktitle = {Artificial Neural Networks and Machine Learning – ICANN 2013},
    citeulike-article-id = {13325852},
    citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-642-40728-4\_27},
    citeulike-linkout-1 = {http://link.springer.com/chapter/10.1007/978-3-642-40728-4\_27},
    doi = {10.1007/978-3-642-40728-4\_27},
    editor = {Mladenov, Valeri and Koprinkova-Hristova, Petia and Palm, G\"{u}nther and Villa, Alessandro E. P. and Appollini, Bruno and Kasabov, Nikola},
    keywords = {ann, embodiment, language, model, mtrnn, neurorobotics, robot},
    pages = {216--223},
    posted-at = {2014-08-14 09:50:24},
    priority = {2},
    publisher = {Springer Berlin Heidelberg},
    series = {Lecture Notes in Computer Science},
    title = {Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network},
    url = {http://dx.doi.org/10.1007/978-3-642-40728-4\_27},
    volume = {8131},
    year = {2013}
}

See the CiteULike entry for more info, PDF links, BibTex etc.

The model proposed by Heinrich et al. builds upon the one by Hinoshita et al. It adds visual input and thus shows how learning of language may not only be grounded in perception of verbal utterances, but also in visual perception.