论文标题
零射击的十四行诗生成具有话语级别的计划和美学功能
Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features
论文作者
论文摘要
诗歌产生和一般创造性的语言产生通常遭受缺乏大型培训数据的困扰。在本文中，我们提出了一个新颖的框架，以生成不需要诗歌训练的十四行诗。我们设计了一个分层框架，该框架在解码之前计划了诗歌草图。具体而言，内容计划模块对非精美文本进行了培训，以获得话语级的连贯性。然后，押韵模块生成押韵单词，而抛光模块则引入图像和明喻，以实现美学目的。最后，我们设计了一种受约束的解码算法，以施加生成的十四行诗的仪表和侵蚀约束。自动和人类的评估表明，我们的多阶段方法没有诗歌培训，就会产生比几个强大的基线更连贯，诗意和创造性的十四行诗。
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.
