{"url":"/dataset/opus-100","name":"OPUS-100","full_name":null,"description_markdown":"OPUS-100 is an English-centric multilingual corpus covering 100 languages. It was randomly sampled from the OPUS collection.","description_withheld":null,"homepage":"https://opus.nlpl.eu/OPUS-100","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/improving-massively-multilingual-neural","title":"Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation","first_author":"Biao Zhang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"}],"languages":[],"variants":["OPUS-100","opus100"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/opus100","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Helsinki-NLP/opus-100","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/andrejaystevenson/ffffff","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/andrejaystevenson/zzzz","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/andrejaystevenson/opus-100","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/opus","frameworks":["tf","jax"]}],"num_papers_in_archive":78,"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."}