{"url":"/dataset/lemonade","name":"LEMONADE","full_name":null,"description_markdown":"LEMONADE is a large, expert-annotated dataset for event extraction from news articles in 20 languages: English, Spanish, Arabic, French, Italian, Russian, German, Turkish, Burmese, Indonesian, Ukrainian, Korean, Portuguese, Dutch, Somali, Nepali, Chinese, Persian, Hebrew, and Japanese.","description_withheld":null,"homepage":"https://huggingface.co/datasets/stanford-oval/Lemonade","introduced_date":"2025-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/lemonade-a-large-multilingual-expert","title":"LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World","first_author":"Sina J. Semnani","url":null},"license":{"name":"Apache License, Version 2.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Event Extraction","url":"/task/event-extraction","datasets_with_task":"/datasets/task/event-extraction"},{"name":"Event Detection","url":"/task/event-detection","datasets_with_task":"/datasets/task/event-detection"},{"name":"Event Argument Extraction","url":"/task/event-argument-extraction","datasets_with_task":"/datasets/task/event-argument-extraction"},{"name":"Cross-Lingual Entity Linking","url":"/task/cross-lingual-entity-linking","datasets_with_task":"/datasets/task/cross-lingual-entity-linking"},{"name":"Document-level Event Extraction","url":"/task/document-level-event-extraction","datasets_with_task":"/datasets/task/document-level-event-extraction"}],"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":"Dutch","url":"/datasets/language/dutch"},{"name":"Hebrew","url":"/datasets/language/hebrew"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Persian","url":"/datasets/language/persian"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"},{"name":"Burmese","url":"/datasets/language/burmese"},{"name":"Nepali (individual language)","url":"/datasets/language/nepali-individual-language"},{"name":"Somali","url":"/datasets/language/somali"}],"variants":["LEMONADE"],"data_loaders":[],"num_papers_in_archive":1,"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."}