This joke is [MASK]: Recognizing Humor and Offense with Prompting
This is an incremental improvement for NLP systems aiming to better understand humor in human interactions.
The paper tackled humor recognition in NLP using prompting, showing it matches fine-tuning with abundant data and excels in low-resource settings, while also revealing that models may rely on offense cues during transfer.
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.