Generating Thematic Chinese Poetry with Conditional Variational Autoencoder

Computer poetry generation is our first step towards computer writing. Writing must have a theme. The current approaches of using sequence-to-sequence models with attention often produce nonthematic poems. We present a conditional variational autoencoder with augmented word2vec architecture that explicitly represents the topic or theme information. This approach significantly improves the relevance of the generated poems by representing each line of the poem not only in a context-sensitive manner but also in a holistic way that is highly related to the given keyword and the learned topic. The proposed augmented word2vec model further improves the rhythm and symmetry. We also present a straightforward evaluation metric RHYTHM score to automatically measure the rule-consistency of generated poems. Tests show that 45.24% generated poems by our model are judged by humans to be written by real people.