{"url":"/dataset/divemt","name":"DivEMT","full_name":"Post-Editing Effort Across Typologically-diverse Languages","description_markdown":"DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity.","description_withheld":null,"homepage":"https://github.com/gsarti/divemt","introduced_date":"2022-05-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/divemt-neural-machine-translation-post","title":"DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages","first_author":"Gabriele Sarti","url":null},"license":{"name":"GPL 3.0","url":"https://github.com/gsarti/divemt/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tracking","url":"/datasets/modality/tracking"}],"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":"Italian","url":"/datasets/language/italian"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["DivEMT"],"data_loaders":[],"num_papers_in_archive":3,"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."}