论文标题
多基因语言生成
Multi-Figurative Language Generation
论文作者
论文摘要
形象性语言产生是在所需的言语形象中重新设计给定文本的任务，同时仍然忠于原始上下文。我们通过为英语自动生成五种常见的形象形式提供基准，迈出了多位数语言建模的第一步。我们训练MFLAG采用一种在BART之上进行多基因训练的方案，以及将目标形象信息注入编码器的机制；这使得具有目标形式形式的文本从另一种比喻形式产生，而没有平行的形象构句。我们的方法表现优于所有强大的基线。我们还提供了一些定性分析和对不同语音数字之间关系的反思。
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.
