{"url":"/dataset/ccqa","name":"CCQA","full_name":null,"description_markdown":"CCQA is  new web-scale dataset for in-domain model pre-training. CCQA is a novel QA dataset based on the Common Crawl project. Using the readily available schema.org annotation, around 130 million multilingual question-answer pairs are extracted, including about 60 million English data-points.","description_withheld":null,"homepage":"","introduced_date":"2021-10-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/ccqa-a-new-web-scale-question-answering","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","first_author":"Patrick Huber","url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[],"languages":[],"variants":["CCQA"],"data_loaders":[],"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."}