{"url":"/dataset/global-voices","name":"Global Voices","full_name":null,"description_markdown":"Global Voices is a multilingual dataset for evaluating cross-lingual summarization methods. It is extracted from social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-English summarization in 15 languages. \r\n\r\nSource: [Global Voices: Crossing Borders in Automatic News Summarization](/paper/global-voices-crossing-borders-in-automatic)","description_withheld":null,"homepage":"https://forms.gle/gpkJDT6RJWHM1Ztz9","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/global-voices-crossing-borders-in-automatic","title":"Global Voices: Crossing Borders in Automatic News Summarization","first_author":"Khanh Nguyen","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-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":"Bengali","url":"/datasets/language/bengali"},{"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":"Dutch","url":"/datasets/language/dutch"},{"name":"Greek","url":"/datasets/language/greek"},{"name":"Swahili","url":"/datasets/language/swahili"},{"name":"Macedonian","url":"/datasets/language/macedonian"},{"name":"Malagasy","url":"/datasets/language/malagasy"}],"variants":["Global Voices"],"data_loaders":[],"num_papers_in_archive":9,"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."}