{"url":"/dataset/paranmt-50m","name":"PARANMT-50M","full_name":null,"description_markdown":"PARANMT-50M is a dataset for training paraphrastic sentence embeddings. It consists of more than 50 million English-English sentential paraphrase pairs. \r\n\r\nSource: [ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations](https://arxiv.org/pdf/1711.05732v2.pdf)","description_withheld":null,"homepage":"https://www.cs.cmu.edu/~jwieting/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/paranmt-50m-pushing-the-limits-of","title":"ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations","first_author":"John Wieting","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","datasets_with_task":"/datasets/task/semantic-textual-similarity"},{"name":"Paraphrase Generation","url":"/task/paraphrase-generation","datasets_with_task":"/datasets/task/paraphrase-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PARANMT-50M"],"data_loaders":[],"num_papers_in_archive":13,"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."}