@inproceedings{zhang-etal-2022-qiuniu,
    title = "{Q}iu{N}iu: A {C}hinese Lyrics Generation System with Passage-Level Input",
    author = "Zhang, Le  and
      Zhang, Rongsheng  and
      Mao, Xiaoxi  and
      Chang, Yongzhu",
    editor = "Basile, Valerio  and
      Kozareva, Zornitsa  and
      Stajner, Sanja",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.acl-demo.7/",
    doi = "10.18653/v1/2022.acl-demo.7",
    pages = "76--82",
    abstract = "Lyrics generation has been a very popular application of natural language generation. Previous works mainly focused on generating lyrics based on a couple of attributes or keywords, rendering very limited control over the content of the lyrics. In this paper, we demonstrate the QiuNiu, a Chinese lyrics generation system which is conditioned on passage-level text rather than a few attributes or keywords. By using the passage-level text as input, the content of generated lyrics is expected to reflect the nuances of users' needs. The QiuNiu system supports various forms of passage-level input, such as short stories, essays, poetry. The training of it is conducted under the framework of unsupervised machine translation, due to the lack of aligned passage-level text-to-lyrics corpus. We initialize the parameters of QiuNiu with a custom pretrained Chinese GPT-2 model and adopt a two-step process to finetune the model for better alignment between passage-level text and lyrics. Additionally, a postprocess module is used to filter and rerank the generated lyrics to select the ones of highest quality. The demo video of the system is available at \url{https://youtu.be/OCQNzahqWgM}."
}