{"url":"/dataset/finer","name":"Finer","full_name":"Finnish News Corpus for Named Entity Recognition","description_markdown":"Finnish News Corpus for Named Entity Recognition (Finer) is a corpus that consists of 953 articles (193,742 word tokens) with six named entity classes (organization, location, person, product, event,and date). The articles are extracted from the archives of Digitoday, a Finnish online technology news source.","description_withheld":null,"homepage":"https://github.com/mpsilfve/finer-data","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-finnish-news-corpus-for-named-entity","title":"A Finnish News Corpus for Named Entity Recognition","first_author":"Teemu Ruokolainen","url":null},"license":null,"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":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"}],"languages":[{"name":"Finnish","url":"/datasets/language/finnish"}],"variants":["Finer"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mpsilfve/finer","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/finer","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/mpsilfve/finer-data","url":"https://github.com/mpsilfve/finer-data","frameworks":[]}],"num_papers_in_archive":4,"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."}