{"url":"/dataset/hiner-original-1","name":"HiNER-original","full_name":"HiNER: A Large Hindi Named Entity Recognition Dataset","description_markdown":"This dataset releases a significantly sized standard-abiding Hindi NER dataset containing 109,146 sentences and 2,220,856 tokens, annotated with 11 tags.","description_withheld":null,"homepage":"https://github.com/cfiltnlp/HiNER","introduced_date":"2022-04-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/hiner-a-large-hindi-named-entity-recognition","title":"HiNER: A Large Hindi Named Entity Recognition Dataset","first_author":"Rudra Murthy","url":null},"license":{"name":"CC-BY-SA-4.0","url":"https://github.com/cfiltnlp/HiNER/blob/main/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"}],"languages":[{"name":"Hindi","url":"/datasets/language/hindi"}],"variants":["HiNER-original"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cfilt/HiNER-original","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/cfiltnlp/hiner","url":"https://github.com/cfiltnlp/HiNER","frameworks":["tf","pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-hiner-original","task":"Named Entity Recognition (NER)","dataset_variant":"HiNER-original","rows":2,"metrics":["F1-score (Weighted)"],"first_row_in_archive_order":{"model":"cfilt/HiNER-original-xlm-roberta-large","paper":"/paper/hiner-a-large-hindi-named-entity-recognition","metrics":{"F1-score (Weighted)":"88.78"},"code_links":[{"title":"cfiltnlp/hiner","url":"https://github.com/cfiltnlp/hiner"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/hiner-a-large-hindi-named-entity-recognition","title":"HiNER: A Large Hindi Named Entity Recognition Dataset","date":"2022-04-28","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"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."}