"Judge me by my size (noun), do you?'' YodaLib: A Demographic-Aware Humor Generation Framework
This addresses the problem of generating demographic-aware humor for applications like entertainment or social media, but it is incremental as it builds on existing BERT models and focuses on a specific task.
The authors tackled the challenge of automated humor generation by creating YodaLib, a framework that fills blanks in Mad Libs stories while considering audience demographics, and it outperformed a previous semi-automated method and human annotators in evaluations.
The subjective nature of humor makes computerized humor generation a challenging task. We propose an automatic humor generation framework for filling the blanks in Mad Libs stories, while accounting for the demographic backgrounds of the desired audience. We collect a dataset consisting of such stories, which are filled in and judged by carefully selected workers on Amazon Mechanical Turk. We build upon the BERT platform to predict location-biased word fillings in incomplete sentences, and we fine tune BERT to classify location-specific humor in a sentence. We leverage these components to produce YodaLib, a fully-automated Mad Libs style humor generation framework, which selects and ranks appropriate candidate words and sentences in order to generate a coherent and funny story tailored to certain demographics. Our experimental results indicate that YodaLib outperforms a previous semi-automated approach proposed for this task, while also surpassing human annotators in both qualitative and quantitative analyses.