Figurative Language

Figurative language, encompassing metaphors, similes, idioms, sarcasm, and euphemisms, presents a significant challenge for natural language processing (NLP) due to its non-literal and context-dependent nature. Current research focuses on developing and evaluating models, often leveraging large language models (LLMs) and multi-modal approaches, to improve the detection, understanding, and generation of figurative expressions across multiple languages and modalities (text and images). This work is crucial for advancing NLP capabilities in areas such as machine translation, question answering, and authorship attribution, ultimately leading to more nuanced and human-like interactions with AI systems.

Papers