{"url":"/dataset/duolingo-staple-shared-task","name":"Duolingo STAPLE Shared Task","full_name":null,"description_markdown":"This is the dataset for the 2020 Duolingo shared task on Simultaneous Translation And Paraphrase for Language Education (STAPLE). Sentence prompts, along with automatic translations, and high-coverage sets of translation paraphrases weighted by user response are provided in 5 language pairs. Starter code for this task can be found here: github.com/duolingo/duolingo-sharedtask-2020/. More details on the data set and task are available at: sharedtask.duolingo.com","description_withheld":null,"homepage":"https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/38OJR6","introduced_date":"2020-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/simultaneous-translation-and-paraphrase-for","title":"Simultaneous Translation and Paraphrase for Language Education","first_author":"Stephen Mayhew","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Paraphrase Generation","url":"/task/paraphrase-generation","datasets_with_task":"/datasets/task/paraphrase-generation"},{"name":"Translation","url":"/task/translation","datasets_with_task":"/datasets/task/translation"},{"name":"Multilingual NLP","url":"/task/multilingual-nlp","datasets_with_task":"/datasets/task/multilingual-nlp"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Multilingual","url":"/datasets/language/multilingual"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["Duolingo STAPLE Shared Task"],"data_loaders":[],"num_papers_in_archive":10,"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."}