{"url":"/dataset/wikilingua","name":"WikiLingua","full_name":null,"description_markdown":"WikiLingua includes ~770k article and summary pairs in 18 languages from WikiHow. Gold-standard article-summary alignments across languages are extracted by aligning the images that are used to describe each how-to step in an article.\r\n\r\nSource: [https://github.com/esdurmus/Wikilingua](https://github.com/esdurmus/Wikilingua)\r\nImage Source: [Ladhak et al](https://arxiv.org/pdf/2010.03093v1.pdf)","description_withheld":null,"homepage":"https://github.com/esdurmus/Wikilingua","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/wikilingua-a-new-benchmark-dataset-for-cross","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","first_author":"Faisal Ladhak","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":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"},{"name":"Document Summarization","url":"/task/document-summarization","datasets_with_task":"/datasets/task/document-summarization"},{"name":"Cross-Lingual Abstractive Summarization","url":"/task/cross-lingual-abstractive-summarization","datasets_with_task":"/datasets/task/cross-lingual-abstractive-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":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Czech","url":"/datasets/language/czech"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["WikiLingua","WikiLingua (es->en)","WikiLingua (ru->en)","WikiLingua (tr->en)","WikiLingua (vi->en)","wiki_lingua"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/esdurmus/wiki_lingua","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki_lingua","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/esdurmus/Wikilingua","url":"https://github.com/esdurmus/Wikilingua","frameworks":[]}],"num_papers_in_archive":52,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-summarization-on-wikilingua-tr-en","task":"Document Summarization","dataset_variant":"WikiLingua (tr->en)","rows":1,"metrics":["Rouge-L"],"first_row_in_archive_order":{"model":"DOCmT5","paper":"/paper/docmt5-document-level-pretraining-of","metrics":{"Rouge-L":"31.37"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/docmt5-document-level-pretraining-of","title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","date":"2021-12-16","rows_on_this_dataset":1,"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."}