HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge

Abstract

A hyperbole is an intentional and creative exaggeration not to be taken literally. Despite its ubiquity in daily life, the computational explorations of hyperboles are scarce. In this paper, we tackle the under-explored and challenging task: sentence-level hyperbole generation. We start with a representative syntactic pattern for intensification and systematically study the semantic (commonsense and counterfactual) relationships between each component in such hyperboles. Next, we leverage the COMeT and reverse COMeT models to do commonsense and counterfactual inference. We then generate multiple hyperbole candidates based on our findings from the pattern, and train neural classifiers to rank and select high-quality hyperboles. Automatic and human evaluations show that our generation method is able to generate hyperboles creatively with high success rate and intensity scores.

Quantifying Hyperbole: Explicit Estimates of Exaggerated Utterances

“…Ultimately, the multipage definition boils down to a single sentence: "hyperbole is a figure whereby the quantity or quality of an objective fact is, whether purposely or inadvertently, subjectively inflated or deflated in varying degrees but always to excess in an utterance which listeners do not normally interpret literally or perceive as a lie" (Cano Mora, 2006: 108). Indeed, consistent with this definition, most definitions of hyperbole have emphasized the qualities of extremity and exaggeration (e.g., Cano Mora, 2009;Carston & Wearing, 2015;Norrick, 2004;Tian, Sridhar & Peng, 2021) and extreme case formulations (Colston, 2007; but see Christodoulidou, 2009Christodoulidou, , 2011. Claridge (2010) provided a useful preliminary definition of hyperbole by emphasizing the distinction between literal and hyperbolic expressions.…”

TwistList: Resources and Baselines for Tongue Twister Generation

“…Other forms of language where phonemic and phonetic information are essential have also been generated, including rap (Xue et al 2021;Manjavacas, Kestemont, and Karsdorp 2019;Potash, Romanov, and Rumshisky 2018) and song lyrics more generally (Tian et al 2023;Chang et al 2023;Zhang et al 2022). Computational research on creative works is not restricted to such domains, however, with extensive work also existing in the area of narrative generation (Hong et al 2023;Tang et al 2022;Chen et al 2021), humor generation (Loakman, Maladry, and Lin 2023;Sun et al 2022;Tian, Sheth, and Peng 2022;He, Peng, and Liang 2019), metaphor processing (Wang et al 2023;Li et al 2023a;Li, Guerin, and Lin 2022), and music generation (Li et al 2024;Yu et al 2023).…”

MOVER: Mask, Over-generate and Rank for Hyperbole Generation

“…Previous studies have tackled the generation of metaphor (Yu and Wan, 2019;Stowe et al, 2020;Stowe et al, 2021), simile (Chakrabarty et al, 2020b;, idiom (Zhou et al, 2021), pun (Yu et al, 2018;Luo et al, 2019b;He et al, 2019;, and sarcasm (Chakrabarty et al, 2020a). HypoGen (Tian et al, 2021) is a concurrent work with ours on hyperbole generation. However, we share a different point of view and the two methods are not directly comparable.…”

“…Although hyperbole is considered as the second most frequent figurative device (Kreuz and Roberts, 1993), it has received less empirical attention in the NLP community. Recently Tian et al (2021) addressed the generation of clause-level hyperbole. In this paper, we instead focus on word-level and phrase-level hyperbole, which can be unified as span-level hyperbole.…”