{"url":"/dataset/weibo-ner","name":"Weibo NER","full_name":"Weibo NER","description_markdown":"The **Weibo NER** dataset is a Chinese Named Entity Recognition dataset drawn from the social media website Sina Weibo.\r\n\r\nSource: [Chinese NER Using Lattice LSTM](https://arxiv.org/abs/1805.02023)\r\nImage Source: [https://en.wikipedia.org/wiki/Sina_Weibo](https://en.wikipedia.org/wiki/Sina_Weibo)","description_withheld":null,"homepage":"https://github.com/OYE93/Chinese-NLP-Corpus/tree/master/NER/Weibo","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/named-entity-recognition-for-chinese-social","title":"Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings","first_author":"Nanyun Peng","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Fake News Detection","url":"/task/fake-news-detection","datasets_with_task":"/datasets/task/fake-news-detection"},{"name":"Chinese Named Entity Recognition","url":"/task/chinese-named-entity-recognition","datasets_with_task":"/datasets/task/chinese-named-entity-recognition"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Weibo NER"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hltcoe/weibo_ner","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/weibo_ner","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/OYE93/Chinese-NLP-Corpus","url":"https://github.com/OYE93/Chinese-NLP-Corpus","frameworks":[]}],"num_papers_in_archive":52,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/chinese-named-entity-recognition-on-weibo-ner","task":"Chinese Named Entity Recognition","dataset_variant":"Weibo NER","rows":18,"metrics":["F1","Precision","Recall","Accuracy-NE","Accuracy-NM","Overall"],"first_row_in_archive_order":{"model":"BERT-CRF (Replicated in AdaSeq)","paper":"/paper/improving-named-entity-recognition-by","metrics":{"F1":"72.77"},"code_links":[{"title":"modelscope/adaseq","url":"https://github.com/modelscope/adaseq"},{"title":"modelscope/AdaSeq","url":"https://github.com/modelscope/AdaSeq/tree/master/examples/RaNER"},{"title":"Alibaba-NLP/CLNER","url":"https://github.com/Alibaba-NLP/CLNER"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fake-news-detection-on-weibo-ner","task":"Fake News Detection","dataset_variant":"Weibo NER","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SEMI-FND","paper":"/paper/semi-fnd-stacked-ensemble-based-multimodal","metrics":{"Accuracy":"86.83%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-global-context-mechanism-for-sequence","title":"Supplementary Features of BiLSTM for Enhanced Sequence Labeling","date":"2023-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semi-fnd-stacked-ensemble-based-multimodal","title":"SEMI-FND: Stacked Ensemble Based Multimodal Inference For Faster Fake News Detection","date":"2022-05-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/locate-and-label-a-two-stage-identifier-for","title":"Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition","date":"2021-05-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/named-entity-recognition-for-social-media","title":"Named Entity Recognition for Social Media Texts with Semantic Augmentation","date":"2020-10-29","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/tener-adapting-transformer-encoder-for-name","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","date":"2019-11-10","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/leverage-lexical-knowledge-for-chinese-named","title":"Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network","date":"2019-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/adversarial-transfer-learning-for-chinese","title":"Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism","date":"2018-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":15,"samples_ran":5,"samples_unverified":10,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":2,"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."}