Chinese Poetry Generation with a Salient-Clue Mechanism

TL;DR

This paper introduces a Salient-Clue mechanism for Chinese poetry generation that enhances coherence by selecting key characters from generated lines to guide subsequent lines, outperforming existing methods.

Contribution

The novel Salient-Clue mechanism automatically identifies salient characters to improve coherence and allows flexible control over generated poetry styles.

Findings

Outperforms three strong baseline models

Effectively improves coherence in generated poems

Enables style control in poetry generation

Abstract

As a precious part of the human cultural heritage, Chinese poetry has influenced people for generations. Automatic poetry composition is a challenge for AI. In recent years, significant progress has been made in this area benefiting from the development of neural networks. However, the coherence in meaning, theme or even artistic conception for a generated poem as a whole still remains a big problem. In this paper, we propose a novel Salient-Clue mechanism for Chinese poetry generation. Different from previous work which tried to exploit all the context information, our model selects the most salient characters automatically from each so-far generated line to gradually form a salient clue, which is utilized to guide successive poem generation process so as to eliminate interruptions and improve coherence. Besides, our model can be flexibly extended to control the generated poem in different aspects, for example, poetry style, which further enhances the coherence. Experimental results show that our model is very effective, outperforming three strong baselines.