Pun Generation with Surprise

Proceedings of NAACL-HLT 2019, pages 1734–1744 Minneapolis, Minnesota, June 2 - June 7, 2019. c⃝2019 Association for Computational Linguistics 1734 Pun Generation with Surprise He He1∗and Nanyun Peng2∗and Percy Liang1 1Computer Science Department, Stanford University 2Information Sciences Institute, University of Southern California {hehe,pliang}@cs.stanford.edu, npeng@isi.edu Abstract We tackle the problem of generating a pun sen- tence given a pair of homophones (e.g., “died” and “dyed”). Supervised text generation is in- appropriate due to the lack of a large corpus of puns, and even if such a corpus existed, mimicry is at odds with generating novel con- tent. In this paper, we propose an unsuper- vised approach to pun generation using a cor- pus of unhumorous text and what we call the local-global surprisal principle: we posit that in a pun sentence, there is a strong associa- tion between the pun word (e.g., “dyed”) and the distant context, as well as a strong associa- tion between the alternative word (e.g., “died”) and the immediate context. This contrast cre- ates surprise and thus humor. We instanti- ate this principle for pun generation in two ways: (i) as a measure based on the ratio of probabilities under a language model, and (ii) a retrieve-and-edit approach based on words suggested by a skip-gram model. Human evaluation shows that our retrieve-and-edit ap- proach generates puns successfully 31% of the time, tripling the success rate of a neural gen- eration baseline. 1 Introduction Generating creative content is a key require- ment in many natural language generation tasks such as poetry generation (Manurung et al., 2000; Ghazvininejad et al., 2016), story gen- eration (Meehan, 1977; Peng et al., 2018; Fan et al., 2018; Yao et al., 2019), and social chat- bots (Weizenbaum, 1966; Hao et al., 2018). In this paper, we explore creative generation with a focus on puns. We follow the definition of puns in Aarons (2017); Miller et al. (2017): “A pun is a form of wordplay in which one sign (e.g., a word or a phrase) suggests two or more meanings by exploiting polysemy, homonymy, or phonological ∗Equal contribution. Yesterday I accidentally swallowed some food coloring. The doctor says I'm OK, but I feel like I've dyed a little inside. Alternative word: died. Pun word: dyed. Local context Global context Figure 1: An illustration of a homophonic pun. The pun word appears in the sentence, while the alterna- tive word, which has the same pronunciation but differ- ent meaning, is implicated. The local context refers to the immediate words around the pun word, whereas the global context refers to the whole sentence. similarity to another sign, for an intended humor- ous or rhetorical effect.” We focus on a typical class of puns where the ambiguity comes from two (near) homophones. Consider the example in Fig- ure 1: “Yesterday I accidentally swallowed some food coloring. The doctor says I’m OK, but I feel like I’ve dyed (died) a little inside.”. The pun word shown in the sentence (“dyed”) indicates one in- terpretation: the person is colored …

Content truncated to 500 words