{"url":"/dataset/subedits","name":"SubEdits","full_name":null,"description_markdown":"**SubEdits** is a human-annnoated post-editing dataset of neural machine translation outputs, compiled from in-house NMT outputs and human post-edits of subtitles form Rakuten Viki. It is collected from English-German annotations and contains 160k triplets.\r\n\r\nSource: [https://github.com/shamilcm/pedra](https://github.com/shamilcm/pedra)\r\nImage Source: [Chollampatt et al](https://arxiv.org/pdf/2009.14395v1.pdf)","description_withheld":null,"homepage":"https://github.com/shamilcm/pedra","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/can-automatic-post-editing-improve-nmt","title":"Can Automatic Post-Editing Improve NMT?","first_author":"Shamil Chollampatt","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"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":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"}],"variants":["SubEdits"],"data_loaders":[{"repo":"https://github.com/shamilcm/pedra","url":"https://github.com/shamilcm/pedra","frameworks":[]}],"num_papers_in_archive":2,"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."}