%0 Journal Article %T CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset %A Zhu, Qi %A Huang, Kaili %A Zhang, Zheng %A Zhu, Xiaoyan %A Huang, Minlie %J Transactions of the Association for Computational Linguistics %D 2020 %V 8 %I MIT Press %C Cambridge, MA %F zhu-etal-2020-crosswoz %X 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. %R 10.1162/tacl_a_00314 %U https://aclanthology.org/2020.tacl-1.19 %U https://doi.org/10.1162/tacl_a_00314 %P 281-295