{"url":"/dataset/ontonotes-4-0","name":"OntoNotes 4.0","full_name":"OntoNotes Release 4.0","description_markdown":"OntoNotes Release 4.0 contains the content of earlier releases -- OntoNotes Release 1.0 LDC2007T21, OntoNotes Release 2.0 LDC2008T04 and OntoNotes Release 3.0 LDC2009T24 -- and adds newswire, broadcast news, broadcast conversation and web data in English and Chinese and newswire data in Arabic. This cumulative publication consists of 2.4 million words as follows: 300k words of Arabic newswire 250k words of Chinese newswire, 250k words of Chinese broadcast news, 150k words of Chinese broadcast conversation and 150k words of Chinese web text and 600k words of English newswire, 200k word of English broadcast news, 200k words of English broadcast conversation and 300k words of English web text.","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC2011T03","introduced_date":"2011-02-15","introduced_date_note":null,"introduced_by":null,"license":{"name":"LDC User Agreement for Non-Members","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Chinese Named Entity Recognition","url":"/task/chinese-named-entity-recognition","datasets_with_task":"/datasets/task/chinese-named-entity-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Arabic","url":"/datasets/language/arabic"}],"variants":["OntoNotes 4","OntoNotes 4.0"],"data_loaders":[],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/chinese-named-entity-recognition-on-ontonotes","task":"Chinese Named Entity Recognition","dataset_variant":"OntoNotes 4","rows":15,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"BERT-MRC+DSC","paper":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","metrics":{"F1":"84.47"},"code_links":[{"title":"ShannonAI/dice_loss_for_NLP","url":"https://github.com/ShannonAI/dice_loss_for_NLP"},{"title":"fursovia/self-adj-dice","url":"https://github.com/fursovia/self-adj-dice"},{"title":"MindCode-4/code-6","url":"https://github.com/MindCode-4/code-6/tree/main/drop-an-octave-reducing-spatial"},{"title":"MindCode-4/code-11","url":"https://github.com/MindCode-4/code-11/tree/main/dice-loss-for-data-imbalanced-nlp-tasks"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/nflat-non-flat-lattice-transformer-for","title":"NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition","date":"2022-05-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boundary-smoothing-for-named-entity-1","title":"Boundary Smoothing for Named Entity Recognition","date":"2022-04-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-named-entity-recognition-as-word-word","title":"Unified Named Entity Recognition as Word-Word Relation Classification","date":"2021-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-named-entity-recognition-with","title":"Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information","date":"2020-10-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/slk-ner-exploiting-second-order-lexicon","title":"SLK-NER: Exploiting Second-order Lexicon Knowledge for Chinese NER","date":"2020-07-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/flat-chinese-ner-using-flat-lattice","title":"FLAT: Chinese NER Using Flat-Lattice Transformer","date":"2020-04-24","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fgn-fusion-glyph-network-for-chinese-named","title":"FGN: Fusion Glyph Network for Chinese Named Entity Recognition","date":"2020-01-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-lexicon-based-graph-neural-network-for","title":"A Lexicon-Based Graph Neural Network for Chinese NER","date":"2019-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-unified-mrc-framework-for-named-entity","title":"A Unified MRC Framework for Named Entity Recognition","date":"2019-10-25","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simplify-the-usage-of-lexicon-in-chinese-ner","title":"Simplify the Usage of Lexicon in Chinese NER","date":"2019-08-16","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/can-ner-convolutional-attention-network","title":"CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition","date":"2019-04-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chinese-ner-using-lattice-lstm","title":"Chinese NER Using Lattice LSTM","date":"2018-05-05","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"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":4,"samples_harvested":18,"samples_ran":7,"samples_unverified":11,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":1,"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."}