papers AI Learner
The Github is limit! Click to go to the new site.

Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops

2019-02-08
Limor Gultchin (University of Oxford), Genevieve Patterson (TRASH), Nancy Baym (Microsoft Research), Nathaniel Swinger (Lexington High School), Adam Tauman Kalai (Microsoft Research)

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.02783

PDF

http://arxiv.org/pdf/1902.02783


Comments

Content