That's What She Said: Double Entendre Identification

This work identifies a subproblem --- the "that's what she said" problem --- with two distinguishing characteristics: use of nouns that are euphemisms for sexually explicit nouns and structure common in the erotic domain with a classification approach that includes features that model those two characteristics.

Abstract

Humor identification is a hard natural lan-guage understanding problem. We identify a subproblem — the “that’s what she said” problem — with two distinguishing character-istics: (1) use of nouns that are euphemisms for sexually explicit nouns and (2) structure common in the erotic domain. We address this problem in a classification approach that includes features that model those two char-acteristics. Experiments on web data demon-strate that our approach improves precision by 12 % over baseline techniques that use only word-based features. 1