{"url":"/dataset/crosswoz","name":"CrossWOZ","full_name":"CrossWOZ","description_markdown":"**CrossWOZ** is 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 at both user and system sides.\r\n\r\nSource: [CrossWOZ](https://github.com/thu-coai/CrossWOZ)","description_withheld":null,"homepage":"https://github.com/thu-coai/CrossWOZ","introduced_date":"2020-02-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/crosswoz-a-large-scale-chinese-cross-domain","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","first_author":"Qi Zhu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Dialogue State Tracking","url":"/task/dialogue-state-tracking","datasets_with_task":"/datasets/task/dialogue-state-tracking"},{"name":"Task-Oriented Dialogue Systems","url":"/task/task-oriented-dialogue-systems","datasets_with_task":"/datasets/task/task-oriented-dialogue-systems"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"}],"languages":[],"variants":["CrossWOZ"],"data_loaders":[{"repo":"https://github.com/thu-coai/CrossWOZ","url":"https://github.com/thu-coai/CrossWOZ","frameworks":["pytorch"]}],"num_papers_in_archive":25,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}