{"url":"/dataset/peyma","name":"PEYMA","full_name":null,"description_markdown":"Peyma is a Persian NER dataset to train and test NER systems. It is constructed by collecting documents from ten news websites.","description_withheld":null,"homepage":"https://arxiv.org/abs/1801.09936","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/peyma-a-tagged-corpus-for-persian-named","title":"PEYMA: A Tagged Corpus for Persian Named Entities","first_author":"Mahsa Sadat Shahshahani","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"Persian","url":"/datasets/language/persian"}],"variants":["PEYMA"],"data_loaders":[],"num_papers_in_archive":8,"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."}