{"url":"/dataset/parabank","name":"ParaBank","full_name":null,"description_markdown":"A large-scale English paraphrase dataset that surpasses prior work in both quantity and quality.\r\n\r\nSource: [ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation](/paper/parabank-monolingual-bitext-generation-and)","description_withheld":null,"homepage":"http://decomp.io/projects/parabank/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/parabank-monolingual-bitext-generation-and","title":"ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation","first_author":"J. Edward Hu","url":null},"license":null,"modalities":[],"tasks":[{"name":"Causal Inference","url":"/task/causal-inference","datasets_with_task":"/datasets/task/causal-inference"},{"name":"Paraphrase Generation","url":"/task/paraphrase-generation","datasets_with_task":"/datasets/task/paraphrase-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ParaBank"],"data_loaders":[],"num_papers_in_archive":17,"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."}