Multi-Figurative Language Generation

Research output: Contribution to conferencePaperAcademic

6 Downloads (Pure)

Abstract

Figurative language generation is the task of reformulating a given text in the desired figure of speech while still being faithful to the original context. We take the first step towards multi-figurative language modelling by providing a benchmark for the automatic generation of five common figurative forms in English. We train mFLAG employing a scheme for multi-figurative language pre-training on top of BART, and a mechanism for injecting the target figurative information into the encoder; this enables the generation of text with the target figurative form from another figurative form without parallel figurative-figurative sentence pairs. Our approach outperforms all strong baselines. We also offer some qualitative analysis and reflections on the relationship between the different figures of speech.
Original languageEnglish
Publication statusPublished - Oct-2022
Event29th International Conference on Computational Linguistics - Gyeongju, Korea, Republic of
Duration: 12-Oct-202217-Oct-2022

Conference

Conference29th International Conference on Computational Linguistics
Abbreviated titleCOLING 2022
Country/TerritoryKorea, Republic of
CityGyeongju
Period12/10/202217/10/2022

Cite this