Representations of language in a model of visually grounded speech signal
Chrupala,Grzegorz Gelderloos,Lieke Alishahi,Afra
Chrupala,Grzegorz
Gelderloos,Lieke
Alishahi,Afra
Abstract
We present a visually grounded model of speech perception which projects spoken utterances and images to a joint semantic space. We use a multi-layer recurrent highway network to model the temporal nature of spoken speech, and show that it learns to extract both form and meaning-based linguistic knowledge from the input signal. We carry out an in-depth analysis of the representations used by different components of the trained model and show that encoding of semantic aspects tends to become richer as we go up the hierarchy of layers, whereas encoding of form-related aspects of the language input tends to initially increase and then plateau or decrease.
Description
Date
2017
Journal Title
Journal ISSN
Volume Title
Publisher
Association for Computational Linguistics
Research Projects
Organizational Units
Journal Issue
Keywords
Citation
Chrupala, G, Gelderloos, L & Alishahi, A 2017, Representations of language in a model of visually grounded speech signal. in Proceedings of the 55th of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pp. 613–622 , Annual Meeting of the Association for Computational Linguistics 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-1057
License
info:eu-repo/semantics/openAccess