It has been shown that Chinese poems can be successfully generated by
sequence-to-sequence neural models, particularly with the attention mechanism.
A potential problem of this approach, however, is that neural models can only
learn abstract rules, while poem generation is a highly creative process that
involves not only rules but also innovations for which pure statistical models
are not appropriate in principle. This work proposes a memory-augmented neural
model for Chinese poem generation, where the neural model and the augmented
memory work together to balance the requirements of linguistic accordance and
aesthetic innovation, leading to innovative generations that are still
rule-compliant. In addition, it is found that the memory mechanism provides
interesting flexibility that can be used to generate poems with different
styles.

使用增强记忆的神经网络模型在中国古诗文的生成中，通过将神经网络和增强内存结合使用，来平衡规则与美学，实现符合规范和有创意的诗歌生成，并提供了生成不同风格诗歌的灵活性。

利用神经记忆实现灵活创新的中国诗歌生成

Flexible and Creative Chinese Poetry Generation Using Neural Memory

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.

本文利用基于注意力机制的序列到序列模型生成中国宋词。通过双向 LSTM 模型对提示句进行编码，再通过基于注意力的 LSTM 模型预测整个倚仗，可以通过输入线索的细微结构来规范化生成过程。研究了几种技术来改进模型，包括全局上下文整合，混合式风格训练，字符向量初始化和适应性。通过自动和主观评估结果表明，我们的模型确实可以学习到宋词复杂的结构和韵律模式，且生成成功。