Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
This work addresses humor modeling for NLP applications, but it is incremental as it builds on existing word embeddings and humor datasets.
The paper tackled the problem of modeling humor in natural language processing by showing that single-word humor correlates with linear directions in word embeddings, capturing aspects from humor theories and predicting individual differences with a vector representation, based on a dataset of 120,000 words from crowdsourcing and existing ratings.
While humor is often thought to be beyond the reach of Natural Language Processing, we show that several aspects of single-word humor correlate with simple linear directions in Word Embeddings. In particular: (a) the word vectors capture multiple aspects discussed in humor theories from various disciplines; (b) each individual's sense of humor can be represented by a vector, which can predict differences in people's senses of humor on new, unrated, words; and (c) upon clustering humor ratings of multiple demographic groups, different humor preferences emerge across the different groups. Humor ratings are taken from the work of Engelthaler and Hills (2017) as well as from an original crowdsourcing study of 120,000 words. Our dataset further includes annotations for the theoretically-motivated humor features we identify.