{"url":"/dataset/mlsum","name":"MLSUM","full_name":"MultiLingual SUMmarization","description_markdown":"A large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages -- namely, French, German, Spanish, Russian, Turkish. Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization community.\r\n\r\nSource: [MLSUM: The Multilingual Summarization Corpus](/paper/mlsum-the-multilingual-summarization-corpus)","description_withheld":null,"homepage":"https://github.com/recitalAI/MLSUM","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/mlsum-the-multilingual-summarization-corpus","title":"MLSUM: The Multilingual Summarization Corpus","first_author":"Thomas Scialom","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"},{"name":"Summarization","url":"/task/summarization","datasets_with_task":"/datasets/task/summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Turkish","url":"/datasets/language/turkish"}],"variants":["MLSUM","MLSUM de","MLSUM es","mlsum-es","mlsum tu","MLSum-it"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reciTAL/mlsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mlsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/recitalAI/MLSUM","url":"https://github.com/recitalAI/MLSUM","frameworks":[]}],"num_papers_in_archive":45,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/abstractive-text-summarization-on-mlsum-de","task":"Abstractive Text Summarization","dataset_variant":"MLSUM de","rows":1,"metrics":["METEOR"],"first_row_in_archive_order":{"model":"mBART","paper":"/paper/the-gem-benchmark-natural-language-generation","metrics":{"METEOR":"0.437"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/abstractive-text-summarization-on-mlsum-es","task":"Abstractive Text Summarization","dataset_variant":"MLSUM es","rows":1,"metrics":["METEOR"],"first_row_in_archive_order":{"model":"mBART","paper":"/paper/the-gem-benchmark-natural-language-generation","metrics":{"METEOR":"0.210"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/abstractive-text-summarization-on-mlsum-es-1","task":"Abstractive Text Summarization","dataset_variant":"mlsum-es","rows":0,"metrics":["rouge1","rouge2","rougeL","rougeLsum"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/summarization-on-mlsum-de","task":"Summarization","dataset_variant":"MLSUM de","rows":0,"metrics":["Rouge1"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-gem-benchmark-natural-language-generation","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","date":"2021-02-02","rows_on_this_dataset":2,"code_links":0,"syntology":null}],"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."}