Skip to main navigation Skip to search Skip to main content

R3: Reverse, retrieve, and rank for sarcasm generation with commonsense knowledge

  • Educational Testing Service
  • Columbia University
  • University of Southern California

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

50 Scopus citations

Abstract

We propose an unsupervised approach for sarcasm generation based on a non-sarcastic input sentence. Our method employs a retrieve-and-edit framework to instantiate two major characteristics of sarcasm: reversal of valence and semantic incongruity with the context, which could include shared commonsense or world knowledge between the speaker and the listener. While prior works on sarcasm generation predominantly focus on context incongruity, we show that combining valence reversal and semantic incongruity based on commonsense knowledge generates sarcastic messages of higher quality based on several criteria. Human evaluation shows that our system generates sarcasm better than human judges 34% of the time, and better than a reinforced hybrid baseline 90% of the time.

Original languageEnglish
Title of host publicationACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages7976-7986
Number of pages11
ISBN (Electronic)9781952148255
StatePublished - 2020
Event58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Virtual, Online, United States
Duration: Jul 5 2020Jul 10 2020

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Country/TerritoryUnited States
CityVirtual, Online
Period07/5/2007/10/20

Fingerprint

Dive into the research topics of 'R3: Reverse, retrieve, and rank for sarcasm generation with commonsense knowledge'. Together they form a unique fingerprint.

Cite this