@inproceedings{bizzoni-dobnik-2020-sky,
    title = "Sky + Fire = Sunset. Exploring Parallels between Visually Grounded Metaphors and Image Classifiers",
    author = "Bizzoni, Yuri  and
      Dobnik, Simon",
    editor = "Klebanov, Beata Beigman  and
      Shutova, Ekaterina  and
      Lichtenstein, Patricia  and
      Muresan, Smaranda  and
      Wee, Chee  and
      Feldman, Anna  and
      Ghosh, Debanjan",
    booktitle = "Proceedings of the Second Workshop on Figurative Language Processing",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.figlang-1.19/",
    doi = "10.18653/v1/2020.figlang-1.19",
    pages = "126--135",
    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."
}