HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge

Yufei Tian, Arvind krishna Sridhar, Nanyun Peng


Abstract
A hyperbole is an intentional and creative exaggeration not to be taken literally. Despite its ubiquity in daily life, the computational explorations of hyperboles are scarce. In this paper, we tackle the under-explored and challenging task: sentence-level hyperbole generation. We start with a representative syntactic pattern for intensification and systematically study the semantic (commonsense and counterfactual) relationships between each component in such hyperboles. We then leverage commonsense and counterfactual inference to generate hyperbole candidates based on our findings from the pattern, and train neural classifiers to rank and select high-quality hyperboles. Automatic and human evaluations show that our generation method is able to generate hyperboles with high success rate, intensity, funniness, and creativity.
Anthology ID:
2021.findings-emnlp.136
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1583–1593
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.136
DOI:
10.18653/v1/2021.findings-emnlp.136
Bibkey:
Cite (ACL):
Yufei Tian, Arvind krishna Sridhar, and Nanyun Peng. 2021. HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1583–1593, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge (Tian et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.136.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.136.mp4
Code
 ninatian98369/hypogen
Data
ConceptNet