Pun Generation
Pun generation research focuses on understanding and replicating the human ability to create humorous wordplay, primarily using large language models (LLMs) and multimodal approaches incorporating visual cues. Current research explores various aspects, including pun recognition, generation, and explanation, often employing techniques like prompt engineering and pre-training on user behavior data to improve model performance. This work contributes to a broader understanding of humor, language processing, and multimodal reasoning, with potential applications in creative writing, chatbot development, and even social media bot detection.
Papers
Context-Situated Pun Generation
Jiao Sun, Anjali Narayan-Chen, Shereen Oraby, Shuyang Gao, Tagyoung Chung, Jing Huang, Yang Liu, Nanyun Peng
ExPUNations: Augmenting Puns with Keywords and Explanations
Jiao Sun, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Tagyoung Chung, Jing Huang, Yang Liu, Nanyun Peng
A Unified Framework for Pun Generation with Humor Principles
Yufei Tian, Divyanshu Sheth, Nanyun Peng