Chinese Poetry Generation with Planning based Neural Network
This addresses the challenge of generating coherent and intent-aligned Chinese poetry, which is an incremental improvement for natural language processing applications.
The authors tackled Chinese poetry generation by proposing a two-stage method that plans sub-topics based on user intent and then generates lines sequentially, resulting in outperforming state-of-the-art methods and achieving poem quality comparable to human poets.
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.