MOVER: Mask, Over-generate and Rank for Hyperbole Generation
Despite being a common figure of speech, hyperbole is under-researched in Figurative Language Processing. In this paper, we tackle the challenging task of hyperbole generation to transfer a literal sentence into its hyperbolic paraphrase. To address the lack of available hyperbolic sentences, we construct HYPO-XL, the first large-scale English hyperbole corpus containing 17,862 hyperbolic sentences in a non-trivial way. Based on our corpus, we propose an unsupervised method for hyperbole generation that does not require 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. Automatic and human evaluation results show that our model is effective at generating hyperbolic paraphrase sentences and outperforms several baseline systems.
Code (1)
Tasks
SentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MOVER: Mask, Over-generate and Rank for Hyperbole Generation
Despite being a common figure of speech, hyperbole is under-researched in Figurative Language Processing. In this paper, we tackle the challenging task of hyperbole generation to transfer a literal sentence into its hype…
SentenceHypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge
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 …
counterfactualCounterfactual InferenceSentenceTask-Decoupled Image Inpainting Framework for Class-specific Object Remover
Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance. Existing works on object removal erase removal targets using image inpainting networks. However, i…
Image InpaintingObjectHarnessing Privileged Information for Hyperbole Detection
The detection of hyperbole is an important stepping stone to understanding the intentions of a hyperbolic utterance. We propose a model that combines pre-trained language models with privileged information for the task o…
A Match Made in Heaven: A Multi-task Framework for Hyperbole and Metaphor Detection
Hyperbole and metaphor are common in day-to-day communication (e.g., "I am in deep trouble": how does trouble have depth?), which makes their detection important, especially in a conversational AI setting. Existing appro…
Multi-Task Learning