Timezone: »

Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
Limor Gultchin · Genevieve Patterson · Nancy Baym · Nathaniel Swinger · Adam Kalai

Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Room 104

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.

Author Information

Limor Gultchin (University of Oxford)
Genevieve Patterson (TRASH)
Nancy Baym (Micr)
Nathaniel Swinger (Lexington High School)
Adam Kalai (Microsoft Research)

Related Events (a corresponding poster, oral, or spotlight)