Chinese Poetry Generation with Planning based Neural Network

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.

arXiv commentAccepted paper at COLING 2016

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• ADADELTA: An Adaptive Learning Rate Method
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Chinese Song Iambics Generation with Neural Attention-based Model
• Generating Chinese Classical Poems with RNN Encoder-Decoder

Cited by in corpus (17)

• PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
• GPT-based Generation for Classical Chinese Poetry
• Image Inspired Poetry Generation in XiaoIce
• A Multi-Modal Chinese Poetry Generation Model
• A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation
• Theme-aware generation model for chinese lyrics
• DYPLODOC: Dynamic Plots for Document Classification
• Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders
• AfriKI: Machine-in-the-Loop Afrikaans Poetry Generation
• Generating Classical Chinese Poems from Vernacular Chinese
• There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It
• Generating Major Types of Chinese Classical Poetry in a Uniformed Framework
• Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines
• A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
• Correction of Faulty Background Knowledge based on Condition Aware and Revise Transformer for Question Answering
• WakaVT: A Sequential Variational Transformer for Waka Generation
• Chinese Poetry Generation with Flexible Styles