{"url":"/dataset/armenian-paraphrase-detection-corpus","name":"Armenian Paraphrase Detection Corpus","full_name":null,"description_markdown":"This dataset contains 2,360 paraphrases in Armenian that can be used for paraphrase detection. The dataset is constructed by back-translating sentences from Armenian to English twice, and manually filtering the result.\n\nSource: [https://github.com/ivannikov-lab/arpa-paraphrase-corpus](https://github.com/ivannikov-lab/arpa-paraphrase-corpus)","description_withheld":null,"homepage":"https://github.com/ivannikov-lab/arpa-paraphrase-corpus","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/arpa-armenian-paraphrase-detection-corpus-and","title":"ARPA: Armenian Paraphrase Detection Corpus and Models","first_author":"Arthur Malajyan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Armenian","url":"/datasets/language/armenian"}],"variants":["Armenian Paraphrase Detection Corpus"],"data_loaders":[{"repo":"https://github.com/ivannikov-lab/arpa-paraphrase-corpus","url":"https://github.com/ivannikov-lab/arpa-paraphrase-corpus","frameworks":[]}],"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":"2026-09-25T09:33:49+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."}