{"url":"/dataset/escape","name":"eSCAPE","full_name":null,"description_markdown":"Consists of millions of entries in which the MT element of the training triplets has been obtained by translating the source side of publicly-available parallel corpora, and using the target side as an artificial human post-edit. Translations are obtained both with phrase-based and neural models.\r\n\r\nSource: [eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing](/paper/escape-a-large-scale-synthetic-corpus-for)","description_withheld":null,"homepage":"http://hltshare.fbk.eu/QT21/eSCAPE.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/escape-a-large-scale-synthetic-corpus-for","title":"eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing","first_author":"Matteo Negri","url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Automatic Post-Editing","url":"/task/automatic-post-editing","datasets_with_task":"/datasets/task/automatic-post-editing"}],"languages":[],"variants":["eSCAPE"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/gsarti/escape","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":28,"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."}