{"url":"/dataset/wiki-zh","name":"Wiki-zh","full_name":null,"description_markdown":"**Wiki-zh** is an annotated Chinese dataset for domain detection extracted from Wikipedia. It includes texts from 7 different domains: “Business and Commerce” (BUS), “Government and Politics” (GOV), “Physical and Mental Health” (HEA), “Law and Order” (LAW), “Lifestyle” (LIF), “Military” (MIL), and “General Purpose” (GEN). It contains 26,280 documents split into training, validation and test.\n\nSource: [https://arxiv.org/pdf/1907.11499.pdf](https://arxiv.org/pdf/1907.11499.pdf)","description_withheld":null,"homepage":"https://github.com/yumoxu/detnet","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/weakly-supervised-domain-detection","title":"Weakly Supervised Domain Detection","first_author":"Yumo Xu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Multiple Instance Learning","url":"/task/multiple-instance-learning","datasets_with_task":"/datasets/task/multiple-instance-learning"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Wiki-zh"],"data_loaders":[{"repo":"https://github.com/yumoxu/detnet","url":"https://github.com/yumoxu/detnet","frameworks":[]}],"num_papers_in_archive":1,"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."}