"Judge me by my size (noun), do you?'' YodaLib: A Demographic-Aware Humor Generation Framework

TL;DR

YodaLib is an automated, demographic-aware humor generation framework that creates tailored, funny Mad Libs stories by leveraging BERT for context-aware word prediction and humor classification, outperforming previous methods and human judges.

Contribution

It introduces a novel demographic-aware humor generation framework using BERT, capable of producing tailored humor content that surpasses prior semi-automated approaches and human performance.

Findings

YodaLib outperforms previous semi-automated methods.

YodaLib surpasses human judges in humor quality.

The framework effectively tailors humor to demographic backgrounds.

Abstract

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.