MOVER: Mask, Over-generate and Rank for Hyperbole Generation release_q4quijrky5cellfnxheoxtaa4a

by Yunxiang Zhang, Xiaojun Wan

Released as a article .

2021  

Abstract

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.
In text/plain format

Archived Files and Locations

application/pdf  397.3 kB
file_usfxpm5ehjdvlflrjwah2yqadi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-09-16
Version   v1
Language   en ?
arXiv  2109.07726v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 2116bcb6-b3a4-45bd-8d9e-2fbc1e60b036
API URL: JSON