This joke is [MASK]: Recognizing Humor and Offense with Prompting

Junze Li, Mengjie Zhao, Yubo Xie, Antonis Maronikolakis, Pearl Pu, Hinrich Schuetze
Proceedings of The 1st Transfer Learning for Natural Language Processing Workshop, PMLR 203:1-9, 2023.

Abstract

Humor is a magnetic component in everyday human interactions and communications. Computationally modeling humor enables NLP systems to entertain and engage with users. We investigate the effectiveness of prompting, a new transfer learning paradigm for NLP, for humor recognition. We show that prompting performs similarly to finetuning when numerous annotations are available, but gives stellar performance in low-resource humor recognition. The relationship between humor and offense is also inspected by applying influence functions to prompting; we show that models could rely on offense to determine humor during transfer.

Cite this Paper


BibTeX
@InProceedings{pmlr-v203-li23a, title = {This joke is [MASK]: Recognizing Humor and Offense with Prompting}, author = {Li, Junze and Zhao, Mengjie and Xie, Yubo and Maronikolakis, Antonis and Pu, Pearl and Schuetze, Hinrich}, booktitle = {Proceedings of The 1st Transfer Learning for Natural Language Processing Workshop}, pages = {1--9}, year = {2023}, editor = {Albalak, Alon and Zhou, Chunting and Raffel, Colin and Ramachandran, Deepak and Ruder, Sebastian and Ma, Xuezhe}, volume = {203}, series = {Proceedings of Machine Learning Research}, month = {03 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v203/li23a/li23a.pdf}, url = {https://proceedings.mlr.press/v203/li23a.html}, abstract = {Humor is a magnetic component in everyday human interactions and communications. Computationally modeling humor enables NLP systems to entertain and engage with users. We investigate the effectiveness of prompting, a new transfer learning paradigm for NLP, for humor recognition. We show that prompting performs similarly to finetuning when numerous annotations are available, but gives stellar performance in low-resource humor recognition. The relationship between humor and offense is also inspected by applying influence functions to prompting; we show that models could rely on offense to determine humor during transfer.} }
Endnote
%0 Conference Paper %T This joke is [MASK]: Recognizing Humor and Offense with Prompting %A Junze Li %A Mengjie Zhao %A Yubo Xie %A Antonis Maronikolakis %A Pearl Pu %A Hinrich Schuetze %B Proceedings of The 1st Transfer Learning for Natural Language Processing Workshop %C Proceedings of Machine Learning Research %D 2023 %E Alon Albalak %E Chunting Zhou %E Colin Raffel %E Deepak Ramachandran %E Sebastian Ruder %E Xuezhe Ma %F pmlr-v203-li23a %I PMLR %P 1--9 %U https://proceedings.mlr.press/v203/li23a.html %V 203 %X Humor is a magnetic component in everyday human interactions and communications. Computationally modeling humor enables NLP systems to entertain and engage with users. We investigate the effectiveness of prompting, a new transfer learning paradigm for NLP, for humor recognition. We show that prompting performs similarly to finetuning when numerous annotations are available, but gives stellar performance in low-resource humor recognition. The relationship between humor and offense is also inspected by applying influence functions to prompting; we show that models could rely on offense to determine humor during transfer.
APA
Li, J., Zhao, M., Xie, Y., Maronikolakis, A., Pu, P. & Schuetze, H.. (2023). This joke is [MASK]: Recognizing Humor and Offense with Prompting. Proceedings of The 1st Transfer Learning for Natural Language Processing Workshop, in Proceedings of Machine Learning Research 203:1-9 Available from https://proceedings.mlr.press/v203/li23a.html.

Related Material