Deep-speare：诗歌语言、韵律和韵律的联合神经模型
Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme
摘要：
在本文中，我们提出了一个联合架构，捕捉语言，押韵和十四行诗建模的米。我们使用人群和专家的判断来评估生成的诗歌的质量。重音和押韵模型表现得非常好，因为生成的诗歌在很大程度上与人类写的诗歌没有区别。然而，专家评估显示，一个普通的语言模型含蓄地捕捉了韵律，机器生成的诗歌在可读性和情感方面仍然表现不佳。我们的研究表明，专家评价的重要性，诗歌生成，未来的研究应该超越韵/米，并专注于诗歌语言。
英文摘要：
In this paper, we propose a joint architecture that captures language, rhyme and meter for sonnet modelling. We assess the quality of generated poems using crowd and expert judgements. The stress and rhyme models perform very well, as generated poems are largely indistinguishable from human-written poems. Expert evaluation, however, reveals that a vanilla language model captures meter implicitly, and that machine-generated poems still underperform in terms of readability and emotion. Our research shows the importance expert evaluation for poetry generation, and that future research should look beyond rhyme/meter and focus on poetic language.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
