{"url":"/dataset/e2e-refined","name":"E2E Refined","full_name":null,"description_markdown":"**E2E** Refined is a dataset for sentence classification. It consists of 40,560 examples for training, 4,489 for validation, and 4,555 for test. It is a refined version of the well-known MR-to-text\r\nE2E dataset where many deletion/insertion/substitution errors has been fixed.","description_withheld":null,"homepage":"https://github.com/KSKTYM/E2E-refined-dataset","introduced_date":"2022-11-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/e2e-refined-dataset","title":"E2E Refined Dataset","first_author":"Keisuke Toyama","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sentence Classification","url":"/task/sentence-classification","datasets_with_task":"/datasets/task/sentence-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["E2E Refined"],"data_loaders":[],"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":"2026-09-24T18:15:14+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."}