@inproceedings{yang-etal-2018-stylistic,
    title = "Stylistic {C}hinese Poetry Generation via Unsupervised Style Disentanglement",
    author = "Yang, Cheng  and
      Sun, Maosong  and
      Yi, Xiaoyuan  and
      Li, Wenhao",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D18-1430/",
    doi = "10.18653/v1/D18-1430",
    pages = "3960--3969",
    abstract = "The ability to write diverse poems in different styles under the same poetic imagery is an important characteristic of human poetry writing. Most previous works on automatic Chinese poetry generation focused on improving the coherency among lines. Some work explored style transfer but suffered from expensive expert labeling of poem styles. In this paper, we target on stylistic poetry generation in a fully unsupervised manner for the first time. We propose a novel model which requires no supervised style labeling by incorporating mutual information, a concept in information theory, into modeling. Experimental results show that our model is able to generate stylistic poems without losing fluency and coherency."
}