{"url":"/dataset/finnish-paraphrase-corpus","name":"Finnish Paraphrase Corpus","full_name":null,"description_markdown":"Finnish Paraphrase Corpus is a fully manually annotated paraphrase corpus for Finnish containing 53,572 paraphrase pairs harvested from alternative subtitles and news headings. Out of all paraphrase pairs in the corpus 98% are manually classified to be paraphrases at least in their given context, if not in all contexts.","description_withheld":null,"homepage":"http://github.com/TurkuNLP/Turku-paraphrase-corpus","introduced_date":"2021-03-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/finnish-paraphrase-corpus","title":"Finnish Paraphrase Corpus","first_author":"Jenna Kanerva","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"}],"languages":[{"name":"Finnish","url":"/datasets/language/finnish"}],"variants":["Finnish Paraphrase Corpus"],"data_loaders":[{"repo":"https://github.com/TurkuNLP/Turku-paraphrase-corpus","url":"https://github.com/TurkuNLP/Turku-paraphrase-corpus","frameworks":[]}],"num_papers_in_archive":4,"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."}