{"url":"/dataset/nuner","name":"NuNER","full_name":null,"description_markdown":"The dataset used to pre-train NuNER from the NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data\r\n\r\nContains AI-extracted entities, their concepts, and descriptions from the given text","description_withheld":null,"homepage":"https://huggingface.co/datasets/numind/NuNER","introduced_date":"2024-01-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/nuner-entity-recognition-encoder-pre-training","title":"NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data","first_author":"Sergei Bogdanov","url":null},"license":null,"modalities":[],"tasks":[{"name":"Named Entity Recognition","url":"/task/named-entity-recognition-1","datasets_with_task":"/datasets/task/named-entity-recognition-1"},{"name":"NER","url":"/task/cg","datasets_with_task":"/datasets/task/cg"},{"name":"named-entity-recognition","url":"/task/named-entity-recognition","datasets_with_task":"/datasets/task/named-entity-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["NuNER"],"data_loaders":[],"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":"2026-09-25T09:33:49+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."}