A Couch Potato is not a Potato on a Couch: Prompting Strategies, Image Generation, and Compositionality Prediction for Noun Compounds

We explore the role of the visual modality and of vision transformers in predicting the compositionality of English noun compounds.Crucially, we contribute a framework to address the challenge of obtaining adequate images that represent non-compositional compounds (such as couch potato), making it relevant for any image-based approach targeting figurative language.Our method uses prompting strategies and diffusion models to generate images.Comparing and combining our approach with a stateof-the-art text-based approach reveals complementary contributions regarding features as well as degrees of abstractness in compounds.