Rˆ3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

Tuhin Chakrabarty, Debanjan Ghosh, Smaranda Muresan, Nanyun Peng


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 the commonsense knowledge generates sarcasm of higher quality. Human evaluation shows that our system generates sarcasm better than humans 34% of the time, and better than a reinforced hybrid baseline 90% of the time.
Anthology ID:
2020.acl-main.711
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7976–7986
Language:
URL:
https://aclanthology.org/2020.acl-main.711
DOI:
10.18653/v1/2020.acl-main.711
Bibkey:
Cite (ACL):
Tuhin Chakrabarty, Debanjan Ghosh, Smaranda Muresan, and Nanyun Peng. 2020. Rˆ3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7976–7986, Online. Association for Computational Linguistics.
Cite (Informal):
Rˆ3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge (Chakrabarty et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.711.pdf
Dataset:
 2020.acl-main.711.Dataset.pdf
Video:
 http://slideslive.com/38929144