IRFL: Image Recognition of Figurative Language
Submission Type: Regular Long Paper
Submission Track: Resources and Evaluation
Keywords: Figurative Language, Multimodal Figurative Language, Resources
TL;DR: A dataset of multimodal idioms, metaphors, and similes and a benchmark to evaluate vision and language models' understanding of figurative language.
Abstract: Figures of speech such as metaphors, similes, and idioms are integral parts of human communication. They are ubiquitous in many forms of discourse, allowing people to convey complex, abstract ideas and evoke emotion. As figurative forms are often conveyed through multiple modalities (e.g., both text and images), understanding multimodal figurative language is an important AI challenge, weaving together profound vision, language, commonsense and cultural knowledge.
In this work, we develop the Image Recognition of Figurative Language (IRFL) dataset. We leverage human annotation and an automatic pipeline we created to generate a multimodal dataset, and introduce two novel tasks as a benchmark for multimodal figurative language understanding. We experimented with state-of-the-art vision and language models and found that the best (22%) performed substantially worse than humans (97%). We release our dataset, benchmark, and code in hopes of driving the development of models that can better understand figurative language.
Submission Number: 375
Loading