{"url":"/dataset/mlqe-pe","name":"MLQE-PE","full_name":"Multilingual Quality Estimation and Automatic Post-editing Dataset","description_markdown":"The Multilingual Quality Estimation and Automatic Post-editing (**MLQE-PE**) Dataset is a dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE). The dataset contains seven language pairs, with human labels for 9,000 translations per language pair in the following formats: sentence-level direct assessments and post-editing effort, and word-level good/bad labels. It also contains the post-edited sentences, as well as titles of the articles where the sentences were extracted from, and the neural MT models used to translate the text.\n\nSource: [https://github.com/sheffieldnlp/mlqe-pe](https://github.com/sheffieldnlp/mlqe-pe)","description_withheld":null,"homepage":"https://github.com/sheffieldnlp/mlqe-pe","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/mlqe-pe-a-multilingual-quality-estimation-and","title":"MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset","first_author":"Marina Fomicheva","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"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Romanian","url":"/datasets/language/romanian"},{"name":"Nepali (macrolanguage)","url":"/datasets/language/nepali-macrolanguage"},{"name":"Sinhala","url":"/datasets/language/sinhala"}],"variants":["MLQE-PE"],"data_loaders":[{"repo":"https://github.com/sheffieldnlp/mlqe-pe","url":"https://github.com/sheffieldnlp/mlqe-pe","frameworks":[]}],"num_papers_in_archive":20,"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."}