Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese

We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese. Experimental results show that attention focuses on nouns and this behaviour holds true for two very typologically different languages. We also draw parallels betwee...

Full description

Saved in:
Bibliographic Details
Main Authors: Havard, William N., Chevrot, Jean-Pierre, Besacier, Laurent
Format: Conference Proceeding
Language:English
Subjects:
attention mechanism
cross-lingual speech retrieval
grounded language learning
recurrent neural networks
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese. Experimental results show that attention focuses on nouns and this behaviour holds true for two very typologically different languages. We also draw parallels between artificial neural attention and human attention and show that neural attention focuses on word endings as it has been theorised for human attention. Finally, we investigate how two visually grounded monolingual models can be used to perform cross-lingual speech-to-speech retrieval. For both languages, the enriched bilingual (speech-image) corpora with part-of-speech tags and forced alignments are distributed to the community for reproducible research.
ISSN:2379-190X
DOI:10.1109/ICASSP.2019.8683069