{"url":"/dataset/conll-2002","name":"CoNLL 2002","full_name":null,"description_markdown":"The shared task of CoNLL-2002 concerns language-independent named entity recognition. The types of named entities include: persons, locations, organizations and names of miscellaneous entities that do not belong to the previous three groups. The participants of the shared task were offered training and test data for at least two languages. Information sources other than the training data might have been used in this shared task.\r\n\r\nSource: [CoNLL 2002](https://www.clips.uantwerpen.be/conll2002/ner/)\r\nImage Source: [https://www.aclweb.org/anthology/W02-2024.pdf](https://www.aclweb.org/anthology/W02-2024.pdf)","description_withheld":null,"homepage":"https://www.clips.uantwerpen.be/conll2002/ner/","introduced_date":"2002-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition","first_author":null,"url":"https://www.aclweb.org/anthology/W02-2024/"},"license":{"name":"Unknown","url":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":"Cross-Lingual Transfer","url":"/task/cross-lingual-transfer","datasets_with_task":"/datasets/task/cross-lingual-transfer"},{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"},{"name":"Token Classification","url":"/task/token-classification","datasets_with_task":"/datasets/task/token-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Dutch","url":"/datasets/language/dutch"}],"variants":["CoNLL 2002 (Spanish)","CoNLL 2002 (Dutch)","CoNLL 2002","conll2002"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eriktks/conll2002","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tomaarsen/conll2002","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/conll2002","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/Kaggle/kaggle-api","url":"https://www.kaggle.com/datasets/nltkdata/conll-corpora","frameworks":[]}],"num_papers_in_archive":70,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-conll-2002","task":"Named Entity Recognition (NER)","dataset_variant":"CoNLL 2002 (Spanish)","rows":6,"metrics":["F1"],"first_row_in_archive_order":{"model":"ACE + document-context","paper":"/paper/automated-concatenation-of-embeddings-for-1","metrics":{"F1":"95.9"},"code_links":[{"title":"Alibaba-NLP/ACE","url":"https://github.com/Alibaba-NLP/ACE"},{"title":"zhaoyuesun/phee","url":"https://github.com/zhaoyuesun/phee"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/named-entity-recognition-on-conll-2002-dutch","task":"Named Entity Recognition (NER)","dataset_variant":"CoNLL 2002 (Dutch)","rows":6,"metrics":["F1"],"first_row_in_archive_order":{"model":"ACE + document-context","paper":"/paper/automated-concatenation-of-embeddings-for-1","metrics":{"F1":"95.7"},"code_links":[{"title":"Alibaba-NLP/ACE","url":"https://github.com/Alibaba-NLP/ACE"},{"title":"zhaoyuesun/phee","url":"https://github.com/zhaoyuesun/phee"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/token-classification-on-conll2002","task":"Token Classification","dataset_variant":"conll2002","rows":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/flert-document-level-features-for-named","title":"FLERT: Document-Level Features for Named Entity Recognition","date":"2020-11-13","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/automated-concatenation-of-embeddings-for-1","title":"Automated Concatenation of Embeddings for Structured Prediction","date":"2020-10-10","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/exploring-cross-sentence-contexts-for-named","title":"Exploring Cross-sentence Contexts for Named Entity Recognition with BERT","date":"2020-06-02","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/named-entity-recognition-as-dependency","title":"Named Entity Recognition as Dependency Parsing","date":"2020-05-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-architectures-for-nested-ner-through-1","title":"Neural Architectures for Nested NER through Linearization","date":"2019-08-19","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":17,"samples_ran":4,"samples_unverified":13,"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."}