EDDIE : End-to-End Humor Generation Model with Keyword Control

Abstract

Humor is a common experience that has great societal value. However, humor generation is a challenging problem for the language technologies community as it involves a significant understanding of context. To address this, previous works on humor generation have employed linguistic expertise to produce jokes with a set structure. However this approach is not scalable, since there is a wide range of possible joke structures across various types of jokes (e.g. question-answer formats, one-liners, etc.). In addition, studies on topic-controlled joke generation has been limited, which can hinder the usability of such models in real life. Topic control is important since jokes are often used in a specific context or setting, and choosing the right topic for the setting is crucial for a good use of a joke. This work introduces EDDIE, a keyword-based humor generation model that allows the user to have a fine-grained topic control on the jokes produced. Our system primarily focuses on producing Question and Answer (Q&A) style jokes with occasional one-liners. We have developed a humor generation pipeline that incorporates humor classifier, humor generator, and toxicity filter in order to produce responsible and humorous content. We evaluate EDDIE in a quantitative and qualitative manner. For the former evaluation, we assess the ability of various language models to learn and utilize mechanisms of humor given no linguistic knowledge. For the latter, we have designed three evaluation criteria : funniness, understandability, and complexity. The study has been conducted with both expert comedians and general volunteers from the general public in order to gain insights into machine humor generation and its application in real life.