Chinese Poetry Generation with Planning based Neural Network

TL;DR

This paper introduces a two-stage neural network approach for Chinese poetry generation that plans sub-topics based on user intent and then generates poem lines, resulting in more coherent and semantically aligned poems.

Contribution

It presents a novel planning-based neural network framework that improves coherence and semantic consistency in Chinese poetry generation compared to existing methods.

Findings

Outperforms state-of-the-art poetry generation methods

Produces poems with coherence and semantic alignment comparable to human poets

Human evaluation confirms improved poem quality

Abstract

Chinese poetry generation is a very challenging task in natural language processing. In this paper, we propose a novel two-stage poetry generating method which first plans the sub-topics of the poem according to the user's writing intent, and then generates each line of the poem sequentially, using a modified recurrent neural network encoder-decoder framework. The proposed planning-based method can ensure that the generated poem is coherent and semantically consistent with the user's intent. A comprehensive evaluation with human judgments demonstrates that our proposed approach outperforms the state-of-the-art poetry generating methods and the poem quality is somehow comparable to human poets.