A Unified Framework for Pun Generation with Humor Principles

Yufei Tian, Divyanshu Sheth, Nanyun Peng


Abstract
We propose a unified framework to generate both homophonic and homographic puns to resolve the split-up in existing works. Specifically, we incorporate three linguistic attributes of puns to the language models: ambiguity, distinctiveness, and surprise. Our framework consists of three parts: 1) a context words/phrases selector to promote the aforementioned attributes, 2) a generation model trained on non-pun sentences to incorporate the context words/phrases into the generation output, and 3) a label predictor that learns the structure of puns which is used to steer the generation model at inference time. Evaluation results on both pun types demonstrate the efficacy of our model over strong baselines.
Anthology ID:
2022.findings-emnlp.237
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3253–3261
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.237
DOI:
10.18653/v1/2022.findings-emnlp.237
Bibkey:
Cite (ACL):
Yufei Tian, Divyanshu Sheth, and Nanyun Peng. 2022. A Unified Framework for Pun Generation with Humor Principles. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3253–3261, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
A Unified Framework for Pun Generation with Humor Principles (Tian et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.237.pdf