Automating Humor: A Novel Approach to Joke Generation Using Template Extraction and Infilling
Mayank Goel
Abstract
This paper presents a novel approach to humor generation in natural language processing by automating the creation of jokes through template extraction and infilling. Traditional methods have relied on predefined templates or neural network models, which either lack complexity or fail to produce genuinely humorous content. Our method introduces a technique to extract templates from existing jokes based on semantic salience and BERT’s attention weights. We then infill these templates using advanced techniques, through BERT and large language models (LLMs) like GPT-4, to generate new jokes. Our results indicate that the generated jokes are novel and human-like, with BERT showing promise in generating funny content and GPT-4 excelling in creating clever jokes. The study contributes to a deeper understanding of humor generation and the potential of AI in creative domains.
Relevance Assessment
Research Gap
This is only partially relevant to creativity as a whole, and the creative degree of the outputs is not measured.
Notes
Notes are automatically saved as you type