{"url":"/dataset/pioner","name":"pioNER","full_name":null,"description_markdown":"The **pioNER** corpus provides gold-standard and automatically generated named-entity datasets for the Armenian language.\nThe automatically generated corpus is generated from Wikipedia. The gold-standard set is a collection of over 250 news articles from iLur.am with manual named-entity annotation. It includes sentences from political, sports, local and world news, and is comparable in size with the test sets of other languages.\n\nSource: [https://github.com/ispras-texterra/pioner](https://github.com/ispras-texterra/pioner)","description_withheld":null,"homepage":"https://github.com/ispras-texterra/pioner","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/pioner-datasets-and-baselines-for-armenian","title":"pioNER: Datasets and Baselines for Armenian Named Entity Recognition","first_author":"Tsolak Ghukasyan","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":"Slot Filling","url":"/task/slot-filling","datasets_with_task":"/datasets/task/slot-filling"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[{"name":"Armenian","url":"/datasets/language/armenian"}],"variants":["pioNER"],"data_loaders":[{"repo":"https://github.com/ispras-texterra/pioner","url":"https://github.com/ispras-texterra/pioner","frameworks":[]}],"num_papers_in_archive":2,"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."}