AmbiPun: Generating Humorous Puns with Ambiguous Context
This addresses the challenge of computational humor generation for natural language processing applications, though it is incremental in its approach.
The paper tackled the problem of generating humorous puns without training on existing pun data by leveraging ambiguous context from word definitions, achieving a 52% success rate in human evaluation and outperforming state-of-the-art models.
In this paper, we propose a simple yet effective way to generate pun sentences that does not require any training on existing puns. Our approach is inspired by humor theories that ambiguity comes from the context rather than the pun word itself. Given a pair of definitions of a pun word, our model first produces a list of related concepts through a reverse dictionary. We then utilize one-shot GPT3 to generate context words and then generate puns incorporating context words from both concepts. Human evaluation shows that our method successfully generates pun 52\% of the time, outperforming well-crafted baselines and the state-of-the-art models by a large margin.