A Computational Model of Linguistic Humor in Puns

Abstract

Humor plays an essential role in human interactions. Precisely what makes something funny, however, remains elusive. While research on natural language understanding has made significant advancements in recent years, there has been little direct integration of humor research with computational models of language understanding. In this paper, we propose two information‐theoretic measures—ambiguity and distinctiveness—derived from a simple model of sentence processing. We test these measures on a set of puns and regular sentences and show that they correlate significantly with human judgments of funniness. Moreover, within a set of puns, the distinctiveness measure distinguishes exceptionally funny puns from mediocre ones. Our work is the first, to our knowledge, to integrate a computational model of general language understanding and humor theory to quantitatively predict humor at a fine‐grained level. We present it as an example of a framework for applying models of language processing to understand higher level linguistic and cognitive phenomena.

Pragmatic and Rhetorical Strategies in the English-Written Jokes

“…Since the earliest times, it has performed an essential role in human interaction (Kao, Levy & Goodman, 2015). In addition, human beings are the only species that laughs (Ashipaoloye, 2013).…”

“…The field of the linguistics of humor is in many ways still in its infancy (Attardo, 2014). For the past five years, linguistic humor research in language has shed light on humorous discourse, for instance, dialogues of the American TV series The Big Bang Theory (Ma & Jiang, 2013), Indonesian stand-up comedy (Afidah & Wahyudi, 2014), Romanian parliamentary discourse by a controversial political figure of Romanian politics, Corneliu Vadim Tudor (Săftoiu & Popescu, 2014), Obama's most memorable speeches (Kayam, 2014), a computational model of linguistics humor in puns (Kao et al, 2015), Dudley's political cartoons (Mwetulundila & Kangira, 2015), English advertisements in India (Chetia, 2015), persuasion in Jesus Christ's Humor (Al-Ameedi & Abdulmajeed, 2016), and controversial humor (Hietalahti, 2016).…”

Pun Generation with Surprise

“…Each word also has a latent meaning assignment variable f controlling whether it is generated from an unconditional unigram language model or a unigram model conditioned on z. Ambiguity is defined as the entropy of the posterior distribution over z given all the words, and distinctiveness is defined as the symmetrized KL-divergence between distributions of the assignment variables given the pun meaning and the alternative meaning respectively. The generative model relies on p(x i | z), which Kao et al (2015) estimates using human ratings of word relatedness. We instead use the skip-gram model described in Section 3.3 as we are interested in a fully-automated system.…”

“…Recently, Yu et al (2018) proposed an unsupervised approach that generates puns from a neural language model by jointly decoding conditioned on both the pun and the alternative words, thus injecting ambiguity to the output sentence. However, Kao et al (2015) showed that ambiguity alone is insufficient to bring humor; the two mean-ings must also be supported by distinct sets of words in the sentence.…”

SemEval-2017 Task 7: Detection and Interpretation of English Puns

“…Most computational treatments of puns to date have focused on generative algorithms Ritchie, 1994, 1997;Ritchie, 2005;Hong and Ong, 2009;Waller et al, 2009;Kawahara, 2010) or modelling their phonological properties (Hempelmann, 2003a,b). However, several studies have explored the detection and interpretation of puns (Yokogawa, 2002;Taylor and Mazlack, 2004;Miller and Gurevych, 2015;Kao et al, 2015;Miller and Turković, 2016;Miller, 2016); the most recent of these focus squarely on computational semantics. In this paper, we present the first organized public evaluation for the computational processing of puns.…”