Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops

Limor Gultchin, Genevieve Patterson, Nancy Baym, Nathaniel Swinger, Adam Kalai
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:2474-2483, 2019.

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v97-gultchin19a, title = {Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops}, author = {Gultchin, Limor and Patterson, Genevieve and Baym, Nancy and Swinger, Nathaniel and Kalai, Adam}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {2474--2483}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/gultchin19a/gultchin19a.pdf}, url = {https://proceedings.mlr.press/v97/gultchin19a.html}, 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.} }
Endnote
%0 Conference Paper %T Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops %A Limor Gultchin %A Genevieve Patterson %A Nancy Baym %A Nathaniel Swinger %A Adam Kalai %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-gultchin19a %I PMLR %P 2474--2483 %U https://proceedings.mlr.press/v97/gultchin19a.html %V 97 %X 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.
APA
Gultchin, L., Patterson, G., Baym, N., Swinger, N. & Kalai, A.. (2019). Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:2474-2483 Available from https://proceedings.mlr.press/v97/gultchin19a.html.

Related Material