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}
}
Downloads: 0
{"_id":"9dJ9kHCvcZCRT27Po","bibbaseid":"heinrich-weber-wermter-embodiedlanguageunderstandingwithamultipletimescalerecurrentneuralnetwork","downloads":0,"creationDate":"2017-09-01T15:59:40.268Z","title":"Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network","author_short":["Heinrich, S.","Weber, C.","Wermter, S."],"year":null,"bibtype":"article","biburl":null,"bibdata":{"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","bibtex":"@article{\n title = {Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network},\n type = {article},\n keywords = {Embodied Language,Language Acquisition,MTRNN},\n websites = {http://www.informatik.uni-hamburg.de/WTM/},\n id = {286c1d24-5a62-3358-949a-372622ebfc80},\n created = {2017-09-01T15:53:51.244Z},\n file_attached = {true},\n profile_id = {80da7853-f7b7-36a9-8e4c-d7ddb2d9e538},\n group_id = {a2333ea3-15a4-3d40-8d36-f0d9590ca926},\n last_modified = {2017-09-01T15:53:51.342Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n 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.},\n bibtype = {article},\n author = {Heinrich, Stefan and Weber, Cornelius and Wermter, Stefan}\n}","author_short":["Heinrich, S.","Weber, C.","Wermter, S."],"urls":{"Paper":"http://bibbase.org/service/mendeley/80da7853-f7b7-36a9-8e4c-d7ddb2d9e538/file/38e77dca-e8cd-c21f-3d98-e213ded538e8/Embodied_Language_Understanding_with_a_Multiple_Timescale_Recurrent_Neural_Network.pdf.pdf","Website":"http://www.informatik.uni-hamburg.de/WTM/"},"bibbaseid":"heinrich-weber-wermter-embodiedlanguageunderstandingwithamultipletimescalerecurrentneuralnetwork","role":"author","keyword":["Embodied Language","Language Acquisition","MTRNN"],"downloads":0},"search_terms":["embodied","language","understanding","multiple","timescale","recurrent","neural","network","heinrich","weber","wermter"],"keywords":["embodied language","language acquisition","mtrnn"],"authorIDs":[]}