{"url":"/dataset/wikineural","name":"WikiNEuRal","full_name":null,"description_markdown":"WikiNEuRal is a high-quality automatically-generated dataset for Multilingual Named Entity Recognition.","description_withheld":null,"homepage":"https://github.com/Babelscape/wikineural","introduced_date":"2021-11-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/wikineural-combined-neural-and-knowledge","title":"WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER","first_author":"Simone Tedeschi","url":null},"license":{"name":"CC BY-SA-NC 4.0","url":"https://github.com/Babelscape/wikineural/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Cross-Lingual Transfer","url":"/task/cross-lingual-transfer","datasets_with_task":"/datasets/task/cross-lingual-transfer"},{"name":"Cross-Lingual NER","url":"/task/cross-lingual-ner","datasets_with_task":"/datasets/task/cross-lingual-ner"},{"name":"Token Classification","url":"/task/token-classification","datasets_with_task":"/datasets/task/token-classification"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"},{"name":"Multilingual Named Entity Recognition","url":"/task/multilingual-named-entity-recognition","datasets_with_task":"/datasets/task/multilingual-named-entity-recognition"}],"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":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Polish","url":"/datasets/language/polish"}],"variants":["WikiNEuRal Russian","WikiNEuRal Polish","WikiNEuRal Portuguese","WikiNEuRal French","WikiNEuRal Dutch","WikiNEuRal Spanish","WikiNEuRal German","WikiNEuRal Italian","WikiNEuRal English","WikiNEuRal"],"data_loaders":[{"repo":"https://github.com/babelscape/wikineural","url":"https://github.com/babelscape/wikineural","frameworks":[]}],"num_papers_in_archive":6,"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."}