{"url":"/dataset/parade","name":"PARADE","full_name":null,"description_markdown":"PARADE contains paraphrases that overlap very little at the lexical and syntactic level but are semantically equivalent based on computer science domain knowledge, as well as non-paraphrases that overlap greatly at the lexical and syntactic level but are not semantically equivalent based on this domain knowledge.\r\n\r\nSource: [PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge](/paper/parade-a-new-dataset-for-paraphrase)","description_withheld":null,"homepage":"https://github.com/heyunh2015/PARADE_dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/parade-a-new-dataset-for-paraphrase","title":"PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge","first_author":"Yun He","url":null},"license":null,"modalities":[],"tasks":[{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"}],"languages":[],"variants":["PARADE"],"data_loaders":[{"repo":"https://github.com/heyunh2015/PARADE_dataset","url":"https://github.com/heyunh2015/PARADE_dataset","frameworks":[]}],"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."}