A Unified Framework for Pun Generation with Humor Principles

Abstract

We propose a unified framework to generate both homophonic and homographic puns to resolve the split-up in existing works. Our framework takes a theoretically motivated approach to incorporate three linguistic attributes of puns to language models: ambiguity, distinctiveness, and surprise. Our framework consists of three parts: 1) a context words/phrases selector to promote the aforementioned humor attributes, 2) a generation model trained on non-pun sentences to incorporate the context words/phrases into the generation output, and 3) a label predictor that learns the structure of puns which is used to steer the generation model at inference time. Evaluation results on both homophonic and homographic puns demonstrate the superiority of our model over strong baselines.