Chinese Song Iambics Generation with Neural Attention-based Model

Abstract

Learning and generating Chinese poems is a charming yet challenging task. Traditional approaches involve various language modeling and machine translation techniques, however, they perform not as well when generating poems with complex pattern constraints, for example Song iambics, a famous type of poems that involve variable-length sentences and strict rhythmic patterns. This paper applies the attention-based sequence-to-sequence model to generate Chinese Song iambics. Specifically, we encode the cue sentences by a bi-directional Long-Short Term Memory (LSTM) model and then predict the entire iambic with the information provided by the encoder, in the form of an attention-based LSTM that can regularize the generation process by the fine structure of the input cues. Several techniques are investigated to improve the model, including global context integration, hybrid style training, character vector initialization and adaptation. Both the automatic and subjective evaluation results show that our model indeed can learn the complex structural and rhythmic patterns of Song iambics, and the generation is rather successful.

References in corpus (2)

• ADADELTA: An Adaptive Learning Rate Method
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Cited by in corpus (10)

• Chinese Poetry Generation with Planning based Neural Network
• Image Inspired Poetry Generation in XiaoIce
• A Multi-Modal Chinese Poetry Generation Model
• Generating Chinese Classical Poems with RNN Encoder-Decoder
• Creative GANs for generating poems, lyrics, and metaphors
• Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test
• Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme
• A Syllable-Structured, Contextually-Based Conditionally Generation of Chinese Lyrics
• Generating Chinese Poetry from Images via Concrete and Abstract Information
• Chinese Poetry Generation with Flexible Styles