# Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

arXiv: https://arxiv.org/abs/2012.12007 · HTML: https://mlsanity.com/paper/2012.12007/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [Systematic Literature Review: Computational Approaches for Humour Style Classification](https://mlsanity.com/paper/2402.01759/) (2024)
- [When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity](https://mlsanity.com/paper/2211.01889/) (2022)
- [PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension](https://mlsanity.com/paper/2412.11906/) (2024)
- [Mining Effective Features Using Quantum Entropy for Humor Recognition](https://mlsanity.com/paper/2302.03716/) (2023)
- [Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection](https://mlsanity.com/paper/2402.09055/) (2024)
- [Identifying the Periodicity of Information in Natural Language](https://mlsanity.com/paper/2510.27241/) (2025)
- [On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation](https://mlsanity.com/paper/2602.06423/) (2026)
- [Commonality and Individuality! Integrating Humor Commonality with Speaker Individuality for Humor Recognition](https://mlsanity.com/paper/2502.04960/) (2025)
- [This joke is [MASK]: Recognizing Humor and Offense with Prompting](https://mlsanity.com/paper/2210.13985/) (2022)
- [Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models](https://mlsanity.com/paper/2510.18454/) (2025)
- [RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar](https://mlsanity.com/paper/2607.13189/) (2026)
- [IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English](https://mlsanity.com/paper/2609.15618/) (2026)

## Abstract (arXiv)

Humor recognition has been widely studied as a text classification problem using data-driven approaches. However, most existing work does not examine the actual joke mechanism to understand humor. We break down any joke into two distinct components: the set-up and the punchline, and further explore the special relationship between them. Inspired by the incongruity theory of humor, we model the set-up as the part developing semantic uncertainty, and the punchline disrupting audience expectations. With increasingly powerful language models, we were able to feed the set-up along with the punchline into the GPT-2 language model, and calculate the uncertainty and surprisal values of the jokes. By conducting experiments on the SemEval 2021 Task 7 dataset, we found that these two features have better capabilities of telling jokes from non-jokes, compared with existing baselines.