{"url":"/sota/named-entity-recognition-on-wnut-2017","task":{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","note":null},"dataset":{"name":"WNUT 2017","url":"/dataset/wnut-2017-emerging-and-rare-entity"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Named Entity Recognition (NER)** is a task of Natural Language Processing (NLP) that involves identifying and classifying named entities in a text into predefined categories such as person names, organizations, locations, and others. The goal of NER is to extract structured information from unstructured text data and represent it in a machine-readable format. Approaches typically use BIO notation, which differentiates the beginning (B) and the inside (I) of entities. O is used for non-entity tokens.\r\n\r\nExample:\r\n\r\n| Mark | Watney | visited | Mars |\r\n| --- | ---| --- | --- |\r\n| B-PER | I-PER | O | B-LOC |\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Zalando](https://research.zalando.com/welcome/mission/research-projects/flair-nlp/) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1","F1 (surface form)","Precision","Recall"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher","F1 (surface form)":"higher","Precision":"higher","Recall":"higher"}},"counts":{"rows":23,"rows_with_code":19,"rows_with_paper_page":23,"rows_dated":23,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"CL-KL","metrics":{"F1":"60.45"},"uses_additional_data":false,"paper_date":"2021-05-08","paper":"/paper/improving-named-entity-recognition-by","paper_url":"https://arxiv.org/abs/2105.03654v3","paper_title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","code":"https://github.com/modelscope/adaseq","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"RoBERTa + SubRegWeigh (K-means)","metrics":{"F1":"60.29"},"uses_additional_data":false,"paper_date":"2024-09-10","paper":"/paper/subregweigh-effective-and-efficient","paper_url":"https://arxiv.org/abs/2409.06216v2","paper_title":"SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization","code":"https://github.com/4ldk/SubRegWeigh","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"BERT-CRF (Replicated in AdaSeq)","metrics":{"F1":"59.69"},"uses_additional_data":false,"paper_date":"2021-05-08","paper":"/paper/improving-named-entity-recognition-by","paper_url":"https://arxiv.org/abs/2105.03654v3","paper_title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","code":"https://github.com/modelscope/adaseq","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"RoBERTa-BiLSTM-context","metrics":{"F1":"59.61"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/a-global-context-mechanism-for-sequence","paper_url":"https://arxiv.org/abs/2305.19928v4","paper_title":"Supplementary Features of BiLSTM for Enhanced Sequence Labeling","code":"https://github.com/conglei2xu/global-context-mechanism","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"BERT + RegLER","metrics":{"F1":"58.9"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/regularizing-models-via-pointwise-mutual","paper_url":"https://arxiv.org/abs/2104.07249v2","paper_title":"Regularization for Long Named Entity Recognition","code":"https://github.com/minstar/PMI","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"TNER -xlm-r-large","metrics":{"F1":"58.5"},"uses_additional_data":false,"paper_date":"2022-09-09","paper":"/paper/t-ner-an-all-round-python-library-for-1","paper_url":"https://arxiv.org/abs/2209.12616v1","paper_title":"T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition","code":"https://github.com/asahi417/tner","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":7,"model":"HGN","metrics":{"F1":"57.41"},"uses_additional_data":false,"paper_date":"2022-05-15","paper":"/paper/hero-gang-neural-model-for-named-entity","paper_url":"https://arxiv.org/abs/2205.07177v1","paper_title":"Hero-Gang Neural Model For Named Entity Recognition","code":"https://github.com/jinpeng01/hgn","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"ASA + RoBERTa","metrics":{"F1":"57.3"},"uses_additional_data":false,"paper_date":"2022-06-25","paper":"/paper/adversarial-self-attention-for-language","paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","code":"https://github.com/gingasan/adversarialsa","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"BERTweet","metrics":{"F1":"56.5"},"uses_additional_data":false,"paper_date":"2020-05-20","paper":"/paper/bertweet-a-pre-trained-language-model-for","paper_url":"https://arxiv.org/abs/2005.10200v2","paper_title":"BERTweet: A pre-trained language model for English Tweets","code":"https://github.com/VinAIResearch/BERTweet","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"MINER","metrics":{"F1":"54.86"},"uses_additional_data":false,"paper_date":"2022-04-09","paper":"/paper/miner-improving-out-of-vocabulary-named-1","paper_url":"https://arxiv.org/abs/2204.04391v2","paper_title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","code":"https://github.com/beyonderxx/miner","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"GoLLIE","metrics":{"F1":"54.3"},"uses_additional_data":true,"paper_date":"2023-10-05","paper":"/paper/gollie-annotation-guidelines-improve-zero","paper_url":"https://arxiv.org/abs/2310.03668v5","paper_title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","code":"https://github.com/hitz-zentroa/gollie","n_code_links":1,"syntology":{"n_ran":18,"n_unverified":7,"n_samples":25,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"Truecase","metrics":{"F1":"52.3"},"uses_additional_data":false,"paper_date":"2019-12-15","paper":"/paper/robust-named-entity-recognition-with","paper_url":"https://arxiv.org/abs/1912.07095v1","paper_title":"Robust Named Entity Recognition with Truecasing Pretraining","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"AESINER","metrics":{"F1":"50.68"},"uses_additional_data":false,"paper_date":"2020-10-29","paper":"/paper/improving-named-entity-recognition-with","paper_url":"https://arxiv.org/abs/2010.15466v1","paper_title":"Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information","code":"https://github.com/cuhksz-nlp/AESINER","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"InferNER","metrics":{"F1":"50.52"},"uses_additional_data":false,"paper_date":"2021-04-18","paper":"/paper/inferner-an-attentive-model-leveraging-the","paper_url":"https://journals.flvc.org/FLAIRS/article/view/128538","paper_title":"InferNER: an attentive model leveraging the sentence-level information for Named Entity Recognition in Microblogs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"SA-NER","metrics":{"F1":"50.36"},"uses_additional_data":false,"paper_date":"2020-10-29","paper":"/paper/named-entity-recognition-for-social-media","paper_url":"https://arxiv.org/abs/2010.15458v1","paper_title":"Named Entity Recognition for Social Media Texts with Semantic Augmentation","code":"https://github.com/cuhksz-nlp/SANER","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"CrossWeigh + Pooled Flair","metrics":{"F1":"50.03"},"uses_additional_data":false,"paper_date":"2019-09-03","paper":"/paper/crossweigh-training-named-entity-tagger-from","paper_url":"https://arxiv.org/abs/1909.01441v1","paper_title":"CrossWeigh: Training Named Entity Tagger from Imperfect Annotations","code":"https://github.com/ZihanWangKi/CrossWeigh","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"ASA + BERT-base","metrics":{"F1":"49.8"},"uses_additional_data":false,"paper_date":"2022-06-25","paper":"/paper/adversarial-self-attention-for-language","paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","code":"https://github.com/gingasan/adversarialsa","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"Aguilar et al.","metrics":{"F1":"45.55","F1 (surface form)":"40.24"},"uses_additional_data":false,"paper_date":"2019-06-10","paper":"/paper/modeling-noisiness-to-recognize-named-1","paper_url":"https://arxiv.org/abs/1906.04129v1","paper_title":"Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"NeuralCRF+SAC","metrics":{"F1":"44.77"},"uses_additional_data":false,"paper_date":"2019-11-01","paper":"/paper/similarity-based-auxiliary-classifier-for","paper_url":"https://aclanthology.org/D19-1105","paper_title":"Similarity Based Auxiliary Classifier for Named Entity Recognition","code":"https://github.com/XiaoShiyuan/NCRF-SAC","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"Cross-BiLSTM-CNN","metrics":{"F1":"42.85","Precision":"58.28","Recall":"33.92"},"uses_additional_data":false,"paper_date":"2019-08-29","paper":"/paper/remedying-bilstm-cnn-deficiency-in-modeling","paper_url":"https://arxiv.org/abs/1908.11046v3","paper_title":"Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER","code":"https://github.com/ckiplab/ckiptagger","n_code_links":3,"syntology":null},{"rank_in_archive_order":21,"model":"BiLSTMCRFBP","metrics":{"F1":"42.3"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/regularizing-models-via-pointwise-mutual","paper_url":"https://arxiv.org/abs/2104.07249v2","paper_title":"Regularization for Long Named Entity Recognition","code":"https://github.com/minstar/PMI","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"UH-RiTUAL","metrics":{"F1":"41.86"},"uses_additional_data":false,"paper_date":"2019-06-10","paper":"/paper/a-multi-task-approach-for-named-entity-1","paper_url":"https://arxiv.org/abs/1906.04135v1","paper_title":"A Multi-task Approach for Named Entity Recognition in Social Media Data","code":"https://github.com/tavo91/NER-WNUT17","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"SpinningBytes","metrics":{"F1":"40.78","F1 (surface form)":"39.33"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/transfer-learning-and-sentence-level-features","paper_url":"https://aclanthology.org/W17-4422","paper_title":"Transfer Learning and Sentence Level Features for Named Entity Recognition on Tweets","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":25,"n_unverified":13,"n_samples":38,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":25,"n_unverified":17,"n_samples":42,"n_pointer_only_licence":3,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}