Sky + Fire = Sunset. Exploring Parallels between Visually Grounded Metaphors and Image Classifiers

Yuri Bizzoni, Simon Dobnik


Abstract
This work explores the differences and similarities between neural image classifiers’ mis-categorisations and visually grounded metaphors - that we could conceive as intentional mis-categorisations. We discuss the possibility of using automatic image classifiers to approximate human metaphoric behaviours, and the limitations of such frame. We report two pilot experiments to study grounded metaphoricity. In the first we represent metaphors as a form of visual mis-categorisation. In the second we model metaphors as a more flexible, compositional operation in a continuous visual space generated from automatic classification systems.
Anthology ID:
2020.figlang-1.19
Volume:
Proceedings of the Second Workshop on Figurative Language Processing
Month:
July
Year:
2020
Address:
Online
Editors:
Beata Beigman Klebanov, Ekaterina Shutova, Patricia Lichtenstein, Smaranda Muresan, Chee Wee, Anna Feldman, Debanjan Ghosh
Venue:
Fig-Lang
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
126–135
Language:
URL:
https://aclanthology.org/2020.figlang-1.19
DOI:
10.18653/v1/2020.figlang-1.19
Bibkey:
Cite (ACL):
Yuri Bizzoni and Simon Dobnik. 2020. Sky + Fire = Sunset. Exploring Parallels between Visually Grounded Metaphors and Image Classifiers. In Proceedings of the Second Workshop on Figurative Language Processing, pages 126–135, Online. Association for Computational Linguistics.
Cite (Informal):
Sky + Fire = Sunset. Exploring Parallels between Visually Grounded Metaphors and Image Classifiers (Bizzoni & Dobnik, Fig-Lang 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.figlang-1.19.pdf
Video:
 http://slideslive.com/38929714