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

2020-12-22 · ACL 2021 5 · Yubo Xie, Junze Li, Pearl Pu

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.

📄 PDF Abstract BibTeX arXiv:2012.12007

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling text-classification Text Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Multi-Head Attention 설명 없음

Residual Connection 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Weight Decay 설명 없음

Mining Effective Features Using Quantum Entropy for Humor Recognition

2023-02-07 · Yang Liu, Yuexian Hou

Humor recognition has been extensively studied with different methods in the past years. However, existing studies on humor recognition do not understand the mechanisms that generate humor. In this paper, inspired by the…

The grip of grammar on meaning uncertainty: cross-linguistic evidence, neural correlates, and clinical relevance

2026-05-02 · Rui He, Claudio Palominos, Samuele Vallisa, Ni Yang 외 arxiv

Isolated word meanings are inherently uncertain. This uncertainty reduces when they are combined and anchored in context. We propose that grammar compresses meaning uncertainty cross-linguistically, which is reflected in…

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension

2024-12-16 · Kun Ouyang, Yuanxin Liu, Shicheng Li, Yi Liu 외

Multimodal punchlines, which involve humor or sarcasm conveyed in image-caption pairs, are a popular way of communication on online multimedia platforms. With the rapid development of multimodal large language models (ML…

Benchmarking Image Captioning In-Context Learning

Can Entropy Explain Successor Surprisal Effects in Reading?

2018-10-26 · WS 2019 1 · Marten van Schijndel, Tal Linzen

Human reading behavior is sensitive to surprisal: more predictable words tend to be read faster. Unexpectedly, this applies not only to the surprisal of the word that is currently being read, but also to the surprisal of…

Language Modeling Language Modelling

Effects of Semantic Relatedness between Setups and Punchlines in Twitter Hashtag Games

2016-12-01 · WS 2016 12 · Andrew Cattle, Xiaojuan Ma

This paper explores humour recognition for Twitter-based hashtag games. Given their popularity, frequency, and relatively formulaic nature, these games make a good target for computational humour research and can leverag…

Language Acquisition Sentiment Analysis