{"url":"/dataset/hansel","name":"Hansel","full_name":null,"description_markdown":"Hansel is a human-annotated Chinese entity linking (EL) dataset, focusing on tail entities and emerging entities:\r\n\r\n- The test set contains Few-shot (FS) and zero-shot (ZS) slices, has 10K examples and uses Wikidata as the corresponding knowledge base, useful for testing Chinese/multilingual EL systems' generalization ability to tail and emerging entities.\r\n\r\n- The training and validation sets are from Wikipedia hyperlinks, useful for large-scale pretraining of Chinese EL systems.","description_withheld":null,"homepage":"https://github.com/HITsz-TMG/Hansel","introduced_date":"2022-07-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/hansel-a-chinese-few-shot-and-zero-shot-1","title":"Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark","first_author":"Zhenran Xu","url":null},"license":{"name":"CC-BY-SA","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Entity Disambiguation","url":"/task/entity-disambiguation","datasets_with_task":"/datasets/task/entity-disambiguation"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Hansel"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/HIT-TMG/Hansel","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":2,"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."}