by Chloé Kiddon, Yuriy Brun
Abstract:
Humor identification is a hard natural language understanding problem. We identify a subproblem --- the "that's what she said" problem --- with two distinguishing characteristics: (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 characteristics. Experiments on web data demonstrate that our approach improves precision by 12\% over baseline techniques that use only word-based features.
Citation:
Chloé Kiddon and Yuriy Brun, That's what she said: Double entendre identification, in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL), 2011, pp. 89–94.
Bibtex:
@inproceedings{Kiddon11,
author = {Chlo{\'{e}} Kiddon and Yuriy Brun},
title = {\href{http://people.cs.umass.edu/brun/pubs/pubs/Kiddon11.pdf}{That's
what she said: Double entendre identification}},
booktitle = {Proceedings of the 49th Annual Meeting of the Association for
Computational Linguistics (ACL)},
venue = {ACL},
year = {2011},
month = {June},
date = {19--24},
pages = {89--94},
address = {Portland, {OR}, {USA}},
url = {http://dl.acm.org/citation.cfm?id=2002756},
note = {\href{http://dl.acm.org/citation.cfm?id=2002756}{ACM ID: 2002756}},
abstract = {Humor identification is a hard natural language understanding
problem. We identify a subproblem --- the "that's what she said" problem ---
with two distinguishing characteristics: (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 characteristics. Experiments on web
data demonstrate that our approach improves precision by 12\% over baseline
techniques that use only word-based features.},
fundedBy = {NSF CNS-0937060 to the CRA for the CIFellows Project,
NSF DGE-0718124},
}