Chinese Poetry Generation with Flexible Styles
This work addresses the limitation of existing neural models in producing style-specific poetry, which is important for applications in creative AI and cultural preservation, though it is incremental as it builds on sequence-to-sequence models.
The paper tackles the problem of generating classical Chinese poems with specific styles, such as mimicking the impulsive style of poet Li Bai, by proposing a memory-augmented neural model that stores and uses human-generated style fragments, resulting in flexible style-specific poetry generation.
Research has shown that sequence-to-sequence neural models, particularly those with the attention mechanism, can successfully generate classical Chinese poems. However, neural models are not capable of generating poems that match specific styles, such as the impulsive style of Li Bai, a famous poet in the Tang Dynasty. This work proposes a memory-augmented neural model to enable the generation of style-specific poetry. The key idea is a memory structure that stores how poems with a desired style were generated by humans, and uses similar fragments to adjust the generation. We demonstrate that the proposed algorithm generates poems with flexible styles, including styles of a particular era and an individual poet.