Multi-Figurative Language Generation

Huiyuan Lai, Malvina Nissim


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.
Anthology ID:
2022.coling-1.519
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5939–5954
Language:
URL:
https://aclanthology.org/2022.coling-1.519
DOI:
Bibkey:
Cite (ACL):
Huiyuan Lai and Malvina Nissim. 2022. Multi-Figurative Language Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5939–5954, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Multi-Figurative Language Generation (Lai & Nissim, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.519.pdf
Code
 laihuiyuan/mflag