Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops

Limor Gultchin, Genevieve Patterson, Nancy Baym, Nathaniel Swinger, Adam Tauman Kalai
2/8/2019
cs.CLcs.LGstat.ML

Official code: limorigu/Cockamamie-Gobbledegook (6 stars, last commit 2019-05-15).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

Repo with analysis for the ICML paper Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops

63Jupyter NotebookMay 14, 20197 years ago

Similar Papers

Cite this paper

@article{gultchin2019humor,
  title  = {Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops},
  author = {Limor Gultchin and Genevieve Patterson and Nancy Baym and Nathaniel Swinger and Adam Tauman Kalai},
  year   = {2019},
  eprint = {1902.02783},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1902.02783}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1902.02783.svg)](https://codeofpaper.com/paper/1902.02783)

Discussion