Picture for Nancy Baym

Nancy Baym

Microsoft Research

Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops

Add code
Feb 11, 2019
Limor Gultchin, Genevieve Patterson, Nancy Baym, Nathaniel Swinger, Adam Tauman Kalai

Figure 1 for Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
Figure 2 for Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
Figure 3 for Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
Figure 4 for Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops

We study humor in Word Embeddings, a popular AI tool that associates each word with a Euclidean vector. We find that: (a) the word vectors capture multiple aspects of humor discussed in theories of humor; and (b) each individual's sense of humor can be represented by a vector, and that these sense-of-humor vectors accurately predict differences in people's sense of humor on new, unrated, words. The fact that single-word humor seems to be relatively easy for AI has implications for the study of humor in language. Humor ratings are taken from the work of Englethaler and Hills (2017) as well as our own crowdsourcing study of 120,000 words.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon