A Survey of Pun Generation: Datasets, Evaluations and Methodologies

2025-07-07

AI Summary

Pun generation research lacks a systematic survey, hindering field advancement. This paper presents the first comprehensive review of computational pun generation: it establishes a unified technical taxonomy encompassing rule-based approaches, Seq2Seq models, and prompt-based pretrained language models; systematically catalogs major datasets (e.g., Pun of the Day, PunGenerator) and evaluation methodologies—distinguishing automated metrics (e.g., BLEU, Punscore) from human evaluation criteria; and critically analyzes core challenges in semantic coherence, controllability of pun mechanisms (e.g., homophonic/homographic), and lexical/structural diversity. By synthesizing over two decades of work, this survey fills a critical scholarly gap, introduces standardized evaluation benchmarks, and outlines a clear technology evolution roadmap. It thereby lays the foundation for future research on interpretable, controllable, and high-quality pun generation.

Technology Category

• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Pun generation seeks to creatively modify linguistic elements in text to produce humour or evoke double meanings. It also aims to preserve coherence and contextual appropriateness, making it useful in creative writing and entertainment across various media and contexts. Although pun generation has received considerable attention in computational linguistics, there is currently no dedicated survey that systematically reviews this specific area. To bridge this gap, this paper provides a comprehensive review of pun generation datasets and methods across different stages, including conventional approaches, deep learning techniques, and pre-trained language models. Additionally, we summarise both automated and human evaluation metrics used to assess the quality of pun generation. Finally, we discuss the research challenges and propose promising directions for future work.

Problem

• Lack of systematic survey on pun generation research
• Need to review datasets and methods for pun generation
• Challenges in evaluating pun quality and future directions

Innovation

• Comprehensive review of pun generation datasets
• Analysis of deep learning and language models
• Summary of automated and human evaluation metrics