{"url":"/dataset/wizard-of-oz","name":"Wizard-of-Oz","full_name":null,"description_markdown":"The WoZ 2.0 dataset is a newer dialogue state tracking dataset whose evaluation is detached from the noisy output of speech recognition systems. Similar to DSTC2, it covers the restaurant search domain and has identical evaluation.\r\n\r\nDescription from [NLP Progress](http://nlpprogress.com/english/dialogue.html)\r\n\r\nImage source: [Mrkšić et al.](https://arxiv.org/pdf/1606.03777.pdf)","description_withheld":null,"homepage":"https://arxiv.org/pdf/1606.03777.pdf","introduced_date":"2016-06-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/neural-belief-tracker-data-driven-dialogue","title":"Neural Belief Tracker: Data-Driven Dialogue State Tracking","first_author":"Nikola Mrkšić","url":null},"license":{"name":"Unknown","url":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"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Wizard-of-Oz"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/PolyAI/woz_dialogue","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/woz_dialogue","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#woz-restuarant-reservation-goal-oriented-dialogue","frameworks":["pytorch"]}],"num_papers_in_archive":28,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dialogue-state-tracking-on-wizard-of-oz","task":"Dialogue State Tracking","dataset_variant":"Wizard-of-Oz","rows":10,"metrics":["Joint","Request"],"first_row_in_archive_order":{"model":"AG-DST","paper":"/paper/amendable-generation-for-dialogue-state","metrics":{"Joint":"91.37"},"code_links":[{"title":"PaddlePaddle/Knover","url":"https://github.com/PaddlePaddle/Knover/tree/develop/projects/AG-DST"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/amendable-generation-for-dialogue-state","title":"Amendable Generation for Dialogue State Tracking","date":"2021-10-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/effective-sequence-to-sequence-dialogue-state","title":"Effective Sequence-to-Sequence Dialogue State Tracking","date":"2021-08-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-sequence-to-sequence-approach-to-dialogue","title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","date":"2020-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-simple-but-effective-bert-model-for-dialog","title":"A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems","date":"2019-10-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/scalable-neural-dialogue-state-tracking","title":"Scalable Neural Dialogue State Tracking","date":"2019-10-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/toward-scalable-neural-dialogue-state","title":"Toward Scalable Neural Dialogue State Tracking Model","date":"2018-12-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-universal-dialogue-state-tracking","title":"Towards Universal Dialogue State Tracking","date":"2018-10-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/global-locally-self-attentive-dialogue-state","title":"Global-Locally Self-Attentive Dialogue State Tracker","date":"2018-05-19","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-belief-tracker-data-driven-dialogue","title":"Neural Belief Tracker: Data-Driven Dialogue State Tracking","date":"2016-06-12","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":2,"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."}