GPT-based Generation for Classical Chinese Poetry

TL;DR

This paper introduces a straightforward GPT-based approach for generating high-quality classical Chinese poetry, including various forms and acrostic poems, without complex rules or additional neural components.

Contribution

It is the first to employ GPT for classical Chinese poetry generation, demonstrating effective quality and versatility in poem forms.

Findings

Generated poems are of very high quality.

The method successfully generates various classical Chinese poem forms.

An online demonstration showcases the system's capabilities.

Abstract

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, L\"{u}shi, 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.