Metaphor Annotation

Metaphor annotation focuses on computationally identifying and understanding metaphorical language in text and images, aiming to improve machine comprehension of figurative language. Current research emphasizes developing and evaluating large-scale annotated datasets in multiple languages, exploring the use of large language models (LLMs) and multi-modal models for metaphor detection and generation, and investigating the relationship between metaphor and other linguistic phenomena like hyperbole and sarcasm. This work is significant for advancing natural language processing (NLP) and computer vision, potentially leading to more nuanced and human-like AI systems capable of understanding and generating creative language.