Poetry generation, and creative language generation in general, usually suffers from the lack of large training data. In this paper, we present a novel framework to generate sonnets that does not require training on poems. We design a hierarchical framework which plans the poem sketch before decoding. Specifically, a content planning module is trained on non-poetic texts to obtain discourse-level coherence; then a rhyme module generates rhyme words and a polishing module introduces imagery and similes for aesthetics purposes. Finally, we design a constrained decoding algorithm to impose the meter-and-rhyme constraint of the generated sonnets. Automatic and human evaluation show that our multi-stage approach without training on poem corpora generates more coherent, poetic, and creative sonnets than several strong baselines.
翻译:诗歌的产生和创造性的语言的产生通常缺乏大量的培训数据。 在本文中,我们提出了一个生成不需要诗歌培训的音网的新框架。我们设计了一个等级框架,在解码前规划诗画。具体地说,一个内容规划模块在非诗文文本方面进行了培训,以获得谈话层面的一致性;然后,一个押韵模块生成押韵词,而一个抛光模块为美学目的引入图像和比喻。最后,我们设计了一个有限的解码算法,以强制实施所生成的音网的计量和机能限制。自动和人文评估显示,我们不进行诗体培训的多阶段方法产生比几个强的基线更加连贯、有诗意和创造性的音网。