{"url":"/dataset/conll-2000-1","name":"CoNLL-2000","full_name":null,"description_markdown":"CoNLL-2000 is a dataset for dividing text into syntactically related non-overlapping groups of words, so-called text chunking. \r\n\r\nSource: [https://www.clips.uantwerpen.be/conll2000/chunking/](https://www.clips.uantwerpen.be/conll2000/chunking/)","description_withheld":null,"homepage":"https://www.clips.uantwerpen.be/conll2000/chunking/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"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"},{"name":"Chunking","url":"/task/chunking","datasets_with_task":"/datasets/task/chunking"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CoNLL 2000","CoNLL-2000"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eriktks/conll2000","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/conll2000","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/tagging/dataset_readers/conll2000/","frameworks":["pytorch"]}],"num_papers_in_archive":8,"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."}