{"url":"/dataset/harveyner","name":"HarveyNER","full_name":null,"description_markdown":"fine-grained location names extraction from disaster-related tweets","description_withheld":null,"homepage":"https://github.com/brickee/HarveyNER","introduced_date":"2022-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/crossroads-buildings-and-neighborhoods-a","title":"Crossroads, Buildings and Neighborhoods: A Dataset for Fine-grained Location Recognition","first_author":"Pei Chen","url":null},"license":{"name":"MIT","url":null},"modalities":[],"tasks":[{"name":"NER","url":"/task/cg","datasets_with_task":"/datasets/task/cg"},{"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"}],"languages":[],"variants":["HarveyNER"],"data_loaders":[{"repo":"https://github.com/brickee/harveyner","url":"https://github.com/brickee/harveyner","frameworks":[]}],"num_papers_in_archive":5,"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-2","task":"Zero-shot Named Entity Recognition (NER)","dataset_variant":"HarveyNER","rows":2,"metrics":["Entity F1"],"first_row_in_archive_order":{"model":"GoLLIE","paper":"/paper/gollie-annotation-guidelines-improve-zero","metrics":{"Entity F1":"41.3"},"code_links":[{"title":"hitz-zentroa/gollie","url":"https://github.com/hitz-zentroa/gollie"}]},"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."}}],"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."}