Chinese Song Iambics Generation with Neural Attention-based Model

TL;DR

This paper presents an attention-based neural sequence-to-sequence model for generating Chinese Song iambics, effectively capturing complex rhythmic and structural patterns that traditional methods struggle with.

Contribution

It introduces an attention-based LSTM model with techniques like context integration and style training for improved Chinese poem generation.

Findings

Model successfully learns complex rhythmic patterns.

Generation results are validated by automatic and subjective evaluations.

Techniques improve the quality of generated poems.

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.