{"url":"/dataset/mlsum-it","name":"MLSum-it","full_name":null,"description_markdown":"The MLSum-it dataset is the translated version (Helsinki-NLP/opus-mt-es-it) of the spanish portion of MLSum, containing news articles taken from BBC/mundo.\r\n\r\nThere are two features:\r\n\r\n* source: Input news article.\r\n* target: Summary of the article.","description_withheld":null,"homepage":"https://huggingface.co/datasets/ARTeLab/mlsum-it","introduced_date":"2022-04-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/two-new-datasets-for-italian-language","title":"Two New Datasets for Italian-Language Abstractive Text Summarization","first_author":"Nicola Landro","url":null},"license":null,"modalities":[],"tasks":[{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"}],"languages":[{"name":"Italian","url":"/datasets/language/italian"}],"variants":["MLSum-it"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/abstractive-text-summarization-on-mlsum-it","task":"Abstractive Text Summarization","dataset_variant":"MLSum-it","rows":4,"metrics":["rouge1"],"first_row_in_archive_order":{"model":"mBART","paper":"/paper/two-new-datasets-for-italian-language","metrics":{"rouge1":"19.35"},"code_links":[{"title":"nicolalandro/summarization","url":"https://gitlab.com/nicolalandro/summarization"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/two-new-datasets-for-italian-language","title":"Two New Datasets for Italian-Language Abstractive Text Summarization","date":"2022-04-29","rows_on_this_dataset":4,"code_links":1,"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."}