@article{zhu-etal-2020-crosswoz,
    title = "{C}ross{WOZ}: A Large-Scale {C}hinese Cross-Domain Task-Oriented Dialogue Dataset",
    author = "Zhu, Qi  and
      Huang, Kaili  and
      Zhang, Zheng  and
      Zhu, Xiaoyan  and
      Huang, Minlie",
    editor = "Johnson, Mark  and
      Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "8",
    year = "2020",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.tacl-1.19/",
    doi = "10.1162/tacl_a_00314",
    pages = "281--295",
    abstract = "To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset. It contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi. Moreover, the corpus contains rich annotation of dialogue states and dialogue acts on both user and system sides. About 60{\%} of the dialogues have cross-domain user goals that favor inter-domain dependency and encourage natural transition across domains in conversation. We also provide a user simulator and several benchmark models for pipelined task-oriented dialogue systems, which will facilitate researchers to compare and evaluate their models on this corpus. The large size and rich annotation of CrossWOZ make it suitable to investigate a variety of tasks in cross-domain dialogue modeling, such as dialogue state tracking, policy learning, user simulation, etc."
}