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

Yunxiang Zhang, Xiaojun Wan


Abstract
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.
Anthology ID:
2022.naacl-main.440
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6018–6030
Language:
URL:
https://aclanthology.org/2022.naacl-main.440
DOI:
10.18653/v1/2022.naacl-main.440
Bibkey:
Cite (ACL):
Yunxiang Zhang and Xiaojun Wan. 2022. MOVER: Mask, Over-generate and Rank for Hyperbole Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 6018–6030, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
MOVER: Mask, Over-generate and Rank for Hyperbole Generation (Zhang & Wan, NAACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2022.naacl-main.440.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2022.naacl-main.440.mp4
Code
 yunx-z/mover