{"url":"/dataset/mlqe","name":"MLQE","full_name":"MultiLingual Quality Estimation","description_markdown":"The **MLQE** dataset is a dataset for sentence-level Machine Translation Quality Estimation. It consists of 6 language pairs representing NMT training in high, medium, and low-resource scenarios. The corpus is extracted from Wikipedia, and 10K segments per language pair are annotated.\n\nSource: [https://github.com/facebookresearch/mlqe](https://github.com/facebookresearch/mlqe)","description_withheld":null,"homepage":"https://github.com/facebookresearch/mlqe","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/unsupervised-quality-estimation-for-neural","title":"Unsupervised Quality Estimation for Neural Machine Translation","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"}],"languages":[],"variants":["MLQE"],"data_loaders":[{"repo":"https://github.com/facebookresearch/mlqe","url":"https://github.com/facebookresearch/mlqe","frameworks":[]}],"num_papers_in_archive":5,"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."}