{"url":"/dataset/multi-cpr","name":"Multi-CPR","full_name":"Multi Domain Chinese Dataset for Passage Retrieval","description_markdown":"Multi-CPR is a multi-domain Chinese dataset for passage retrieval. The data is collected from three different domains, including E-commerce, Entertainment video, and Medical. Each dataset contains millions of passages and a certain amount of human-annotated query-passage-related pairs.","description_withheld":null,"homepage":"https://github.com/alibaba-nlp/multi-cpr","introduced_date":"2022-03-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/multi-cpr-a-multi-domain-chinese-dataset-for","title":"Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval","first_author":"Dingkun Long","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Multi-CPR"],"data_loaders":[],"num_papers_in_archive":3,"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."}