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

TL;DR

This paper explores the use of prompting in NLP for humor recognition, demonstrating its effectiveness especially in low-resource settings and revealing how models may associate humor with offense.

Contribution

It introduces prompting as a novel transfer learning approach for humor detection and analyzes the relationship between humor and offense in NLP models.

Findings

Prompting performs comparably to finetuning with ample data.

Prompting excels in low-resource humor recognition.

Models may rely on offensive cues to identify humor.

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.