{"url":"/dataset/crossner","name":"CrossNER","full_name":null,"description_markdown":"CrossNER is a cross-domain NER (Named Entity Recognition) dataset, a fully-labeled collection of NER data spanning over five diverse domains (Politics, Natural Science, Music, Literature, and Artificial Intelligence) with specialized entity categories for different domains. Additionally, CrossNER also includes unlabeled domain-related corpora for the corresponding five domains. \r\n\r\nSource: [CrossNER](https://github.com/zliucr/CrossNER)","description_withheld":null,"homepage":"https://github.com/zliucr/CrossNER","introduced_date":"2020-12-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/crossner-evaluating-cross-domain-named-entity","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","first_author":"Zihan Liu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Zero-shot Named Entity Recognition (NER)","url":"/task/zero-shot-named-entity-recognition-ner","datasets_with_task":"/datasets/task/zero-shot-named-entity-recognition-ner"},{"name":"Cross-Domain Named Entity Recognition","url":"/task/cross-domain-named-entity-recognition","datasets_with_task":"/datasets/task/cross-domain-named-entity-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CrossNER"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eesuhn/crossner-science","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eesuhn/crossner-literature","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eesuhn/crossner-ai","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/zliucr/CrossNER","url":"https://github.com/zliucr/CrossNER","frameworks":["pytorch"]}],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/zero-shot-named-entity-recognition-ner-on-1","task":"Zero-shot Named Entity Recognition (NER)","dataset_variant":"CrossNER","rows":4,"metrics":["AI","Literature","Music","Politics","Science"],"first_row_in_archive_order":{"model":"NuNERZero span","paper":"/paper/nuner-entity-recognition-encoder-pre-training","metrics":{"AI":"61.7","Literature":"64.9","Music":"69.9","Politics":"71.7","Science":"65.4"},"code_links":[{"title":"Serega6678/NuNER","url":"https://github.com/Serega6678/NuNER"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/nuner-entity-recognition-encoder-pre-training","title":"NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data","date":"2024-02-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gollie-annotation-guidelines-improve-zero","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","date":"2023-10-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":25,"samples_ran":18,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/promptner-prompting-for-named-entity","title":"PromptNER: Prompting For Named Entity Recognition","date":"2023-05-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/instructuie-multi-task-instruction-tuning-for","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","date":"2023-04-17","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":25,"samples_ran":18,"samples_unverified":7,"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."}