{"url":"/dataset/statcan-dialogue-dataset","name":"Statcan Dialogue Dataset","full_name":null,"description_markdown":"> **[The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents](https://arxiv.org/abs/2304.01412)**\r\n>\r\n> *[Xing Han Lu](https://xinghanlu.com), [Siva Reddy](https://sivareddy.in), [Harm de Vries](https://www.harmdevries.com/)*\r\n>\r\n> EACL 2023\r\n\r\n| | | | | |\r\n| :--: | :--: | :--: | :--: | :--: |\r\n| [Code](https://github.com/mcGill-NLP/statcan-dialogue-dataset) | [Huggingface](https://huggingface.co/datasets/McGill-NLP/statcan-dialogue-dataset/) | [Request on Dataverse](https://borealisdata.ca/dataset.xhtml?persistentId=doi:10.5683/SP3/NR0BMY) | [Paper](https://arxiv.org/abs/2304.01412) | [Website](https://mcgill-nlp.github.io/statcan-dialogue-dataset) |\r\n\r\n\r\n![Banner](https://github.com/McGill-NLP/statcan-dialogue-dataset/raw/main/images/banner.svg)","description_withheld":null,"homepage":"https://mcgill-nlp.github.io/statcan-dialogue-dataset/","introduced_date":"2023-05-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-statcan-dialogue-dataset-retrieving-data","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","first_author":"Xing Han Lu","url":null},"license":{"name":"Custom","url":"https://borealisdata.ca/dataset.xhtml?persistentId=doi:10.5683/SP3/NR0BMY"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tables","url":"/datasets/modality/tables"}],"tasks":[{"name":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"},{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"},{"name":"Table Retrieval","url":"/task/table-retrieval","datasets_with_task":"/datasets/task/table-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"}],"variants":["Statcan Dialogue Dataset"],"data_loaders":[{"repo":"https://github.com/McGill-NLP/statcan-dialogue-dataset","url":"https://mcgill-nlp.github.io/statcan-dialogue-dataset/docs/","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/table-retrieval-on-statcan-dialogue-dataset","task":"Table Retrieval","dataset_variant":"Statcan Dialogue Dataset","rows":5,"metrics":["Recall@10"],"first_row_in_archive_order":{"model":"DPR (retrieving basic info + member items)","paper":"/paper/the-statcan-dialogue-dataset-retrieving-data","metrics":{"Recall@10":"46.2"},"code_links":[{"title":"McGill-NLP/statcan-dialogue-dataset","url":"https://github.com/McGill-NLP/statcan-dialogue-dataset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-statcan-dialogue-dataset-retrieving-data","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","date":"2023-04-03","rows_on_this_dataset":5,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}