GPT-based Generation for Classical Chinese Poetry
This work addresses poetry generation for cultural and literary applications, but it is incremental as it applies an existing GPT model to a new domain.
The authors tackled the problem of generating classical Chinese poetry by using a simple GPT model without human-crafted rules or additional neural components, achieving very high quality results across various poetic forms including Jueju, Lüshi, Cipai, and Couples.
We present a simple yet effective method for generating high quality classical Chinese poetry with Generative Pre-trained Language Model (GPT). The method adopts a simple GPT model, without using any human crafted rules or features, or designing any additional neural components. While the proposed model learns to generate various forms of classical Chinese poems, including Jueju, Lüshi, various Cipai and Couples, the generated poems are of very high quality. We also propose and implement a method to fine-tune the model to generate acrostic poetry. To the best of our knowledge, this is the first to employ GPT in developing a poetry generation system. We have released an online mini demonstration program on Wechat to show the generation capability of the proposed method for classical Chinese poetry.