Work

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

Year: 2025

Type: conference-paper

Abstract: 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.

DOI: 10.18653/v1/2025.findings-acl.561

Authors: Sinan Kurtyigit, Diego Frassinelli, Carina Silberer, Sabine Schulte Im Walde

Institutions: University of Stuttgart, Technical University of Munich, Ludwig-Maximilians-Universität München

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funder: Deutsche Forschungsgemeinschaft

OpenAlex ID: W4412888391

FWCI:

Cites:

Cited by:

Related to: 10