IRFL: Image Recognition of Figurative Language

27 Mar 2023  ·  Ron Yosef, Yonatan Bitton, Dafna Shahaf ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Classification IRFL: Image Recognition of Figurative Language CLIP-RN50x64 1-of-100 Accuracy 61 # 1
Visual Reasoning IRFL: Image Recognition of Figurative Language Humans 1-of-100 Accuracy 100 # 1

Methods


No methods listed for this paper. Add relevant methods here