Towards Conversational Humor Analysis and Design
This work addresses the challenge of humor generation in conversational AI, which is an incremental improvement over existing methods.
The paper tackled the problem of analyzing and generating conversational humor by focusing on punchline generation from a setup, using a hybrid model that combines rule-based and neural approaches. The result was evaluated through a double-blind study comparing the model's output with human-written jokes, though no concrete numbers are provided in the abstract.
Well-defined jokes can be divided neatly into a setup and a punchline. While most works on humor today talk about a joke as a whole, the idea of generating punchlines to a setup has applications in conversational humor, where funny remarks usually occur with a non-funny context. Thus, this paper is based around two core concepts: Classification and the Generation of a punchline from a particular setup based on the Incongruity Theory. We first implement a feature-based machine learning model to classify humor. For humor generation, we use a neural model, and then merge the classical rule-based approaches with the neural approach to create a hybrid model. The idea behind being: combining insights gained from other tasks with the setup-punchline model and thus applying it to existing text generation approaches. We then use and compare our model with human written jokes with the help of human evaluators in a double-blind study.