Despite being a common figure of speech, hyperbole is under-researched with only a few studies addressing its identification task. In this paper, we introduce a new task of hyperbole generation to transfer a literal sentence into its hyperbolic paraphrase. To tackle the lack of available hyperbolic sentences, we construct HYPO-XL, the first large-scale hyperbole corpus containing 17,862 hyperbolic sentences in a non-trivial way. Based on our corpus, we propose an unsupervised method for hyperbole generation with no need for parallel literal-hyperbole pairs. During training, we fine-tune BART to infill masked hyperbolic spans of sentences from HYPO-XL. During inference, we mask part of an input literal sentence and over-generate multiple possible hyperbolic versions. Then a BERT-based ranker selects the best candidate by hyperbolicity and paraphrase quality. Human evaluation results show that our model is capable of generating hyperbolic paraphrase sentences and outperforms several baseline systems.

本文旨在对夸张的生成进行研究，并构建了首个大规模夸张语料库HYPO-XL，并提出了一种无监督方法，使用BART进行训练和推理，通过遮盖输入字面的句子的一部分和过度生成多个可能的夸张版本来进行生成，同时使用BERT进行排序并选择最佳候选项。 自动和人工评估结果表明，我们的模型效果非常好，优于几种基准系统。

MOVER: 基于掩码、过度生成和排序的夸张生成方法