Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network. Heinrich, S., Weber, C., & Wermter, S.
Paper
Website abstract bibtex How the human brain understands natural language and what we can learn for intelligent systems is open research. Recently, re-searchers 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 characteris-tics of such an architecture and propose a model based on the Multiple Timescale Recurrent Neural Network, extended by embodied visual per-ception. 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.
@article{
title = {Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network},
type = {article},
keywords = {Embodied Language,Language Acquisition,MTRNN},
websites = {http://www.informatik.uni-hamburg.de/WTM/},
id = {286c1d24-5a62-3358-949a-372622ebfc80},
created = {2017-09-01T15:53:51.244Z},
file_attached = {true},
profile_id = {80da7853-f7b7-36a9-8e4c-d7ddb2d9e538},
group_id = {a2333ea3-15a4-3d40-8d36-f0d9590ca926},
last_modified = {2017-09-01T15:53:51.342Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
abstract = {How the human brain understands natural language and what we can learn for intelligent systems is open research. Recently, re-searchers 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 characteris-tics of such an architecture and propose a model based on the Multiple Timescale Recurrent Neural Network, extended by embodied visual per-ception. 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.},
bibtype = {article},
author = {Heinrich, Stefan and Weber, Cornelius and Wermter, Stefan}
}