Multi-Figurative Language Generation
This work addresses the challenge of multi-figurative language generation for natural language processing applications, representing an incremental advance by extending existing methods to handle multiple figures without parallel data.
The paper tackles the problem of generating multiple forms of figurative language from text, achieving state-of-the-art results by outperforming all strong baselines on a new benchmark for five common figurative forms in English.
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.