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
Venues:
ACL | Fig-Lang | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
126–135
Language:
URL:
https://www.aclweb.org/anthology/2020.figlang-1.19
DOI:
10.18653/v1/2020.figlang-1.19
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.figlang-1.19.pdf
Video:
 http://slideslive.com/38929714