Paper  Website  abstract   bibtex   

@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}
}