Self-Attention on Sentence Snippets Incongruity for Humor Assessment

Abstract

Researches on humor identification can advocate a better understanding of human language. Many studies focused on the categorical classification problem of humor, which is less sensible to the intermediate level funny content. Previous work captured the incongruity between words but not sentence snippets. In this paper, a novel method is proposed to exploit snippet-level incongruity features from different aspects, combined with the sentence snippets representations to predict funniness scores. The experiment result shows that this model outperforms most of the competitive methods.