{"url":"/dataset/dogc","name":"DOGC","full_name":null,"description_markdown":"Intended to provide freely available data sets in various formats together with basic annotation to be useful for applications in computational linguistics, translation studies and cross-linguistic corpus studies.\r\n\r\nSource: [Parallel Data, Tools and Interfaces in OPUS](/paper/parallel-data-tools-and-interfaces-in-opus)","description_withheld":null,"homepage":"https://opus.nlpl.eu/DOGC/corpus/version/DOGC","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/parallel-data-tools-and-interfaces-in-opus","title":"Parallel Data, Tools and Interfaces in OPUS","first_author":"J{\\\"o}rg Tiedemann","url":null},"license":{"name":"CC0","url":"https://creativecommons.org/publicdomain/zero/1.0/"},"modalities":[],"tasks":[{"name":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"},{"name":"Word Sense Disambiguation","url":"/task/word-sense-disambiguation","datasets_with_task":"/datasets/task/word-sense-disambiguation"}],"languages":[],"variants":["DOGC"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Helsinki-NLP/opus_dogc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/opus_dogc","frameworks":["tf","pytorch","jax"]}],"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."}