{"url":"/sota/part-of-speech-tagging-on-penn-treebank","task":{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","note":null},"dataset":{"name":"Penn Treebank","url":"/dataset/penn-treebank"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Part-of-speech tagging (POS tagging) is the task of tagging a word in a text with its part of speech.\r\nA part of speech is a category of words with similar grammatical properties. Common English\r\nparts of speech are noun, verb, adjective, adverb, pronoun, preposition, conjunction, etc.\r\n\r\nExample: \r\n\r\n| Vinken | , | 61 | years | old |\r\n| --- | ---| --- | --- | --- |\r\n| NNP | , | CD | NNS | JJ |","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":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":20,"rows_with_code":16,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SALE-BART encoder","metrics":{"Accuracy":"98.15"},"uses_additional_data":false,"paper_date":"2022-07-07","paper":"/paper/sequence-alignment-ensemble-with-a-single","paper_url":"https://ieeexplore.ieee.org/document/9817134","paper_title":"Sequence Alignment Ensemble with a Single Neural Network for Sequence Labeling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Meta BiLSTM","metrics":{"Accuracy":"97.96"},"uses_additional_data":false,"paper_date":"2018-05-21","paper":"/paper/morphosyntactic-tagging-with-a-meta-bilstm","paper_url":"http://arxiv.org/abs/1805.08237v1","paper_title":"Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings","code":"https://github.com/google/meta_tagger","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"Flair embeddings","metrics":{"Accuracy":"97.85"},"uses_additional_data":false,"paper_date":"2018-08-01","paper":"/paper/contextual-string-embeddings-for-sequence","paper_url":"https://aclanthology.org/C18-1139","paper_title":"Contextual String Embeddings for Sequence Labeling","code":"https://github.com/zalandoresearch/flair","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Char Bi-LSTM","metrics":{"Accuracy":"97.78"},"uses_additional_data":false,"paper_date":"2015-08-09","paper":"/paper/finding-function-in-form-compositional-1","paper_url":"http://arxiv.org/abs/1508.02096v2","paper_title":"Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation","code":"https://github.com/wlin12/JNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CVT + Multi-task","metrics":{"Accuracy":"97.76"},"uses_additional_data":false,"paper_date":"2018-09-22","paper":"/paper/semi-supervised-sequence-modeling-with-cross","paper_url":"http://arxiv.org/abs/1809.08370v1","paper_title":"Semi-Supervised Sequence Modeling with Cross-View Training","code":"https://github.com/tensorflow/models","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"SpanRel","metrics":{"Accuracy":"97.7"},"uses_additional_data":false,"paper_date":"2019-11-10","paper":"/paper/generalizing-natural-language-analysis-1","paper_url":"https://arxiv.org/abs/1911.03822v2","paper_title":"Generalizing Natural Language Analysis through Span-relation Representations","code":"https://github.com/jzbjyb/SpanRel","n_code_links":3,"syntology":null},{"rank_in_archive_order":7,"model":"BiLSTM-LAN","metrics":{"Accuracy":"97.65"},"uses_additional_data":false,"paper_date":"2019-08-23","paper":"/paper/hierarchically-refined-label-attention","paper_url":"https://arxiv.org/abs/1908.08676v3","paper_title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","code":"https://github.com/Nealcly/LAN","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"Adversarial Bi-LSTM","metrics":{"Accuracy":"97.59"},"uses_additional_data":false,"paper_date":"2017-11-14","paper":"/paper/robust-multilingual-part-of-speech-tagging","paper_url":"http://arxiv.org/abs/1711.04903v2","paper_title":"Robust Multilingual Part-of-Speech Tagging via Adversarial Training","code":"https://github.com/michiyasunaga/pos_adv","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"IntNet + BiLSTM-CRF","metrics":{"Accuracy":"97.58"},"uses_additional_data":false,"paper_date":"2018-10-29","paper":"/paper/learning-better-internal-structure-of-words","paper_url":"http://arxiv.org/abs/1810.12443v1","paper_title":"Learning Better Internal Structure of Words for Sequence Labeling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"Yang et al.","metrics":{"Accuracy":"97.55"},"uses_additional_data":false,"paper_date":"2017-03-18","paper":"/paper/transfer-learning-for-sequence-tagging-with","paper_url":"http://arxiv.org/abs/1703.06345v1","paper_title":"Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks","code":"https://github.com/jiesutd/NCRFpp","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"BLSTM-CNN-CRF","metrics":{"Accuracy":"97.55"},"uses_additional_data":false,"paper_date":"2016-03-04","paper":"/paper/end-to-end-sequence-labeling-via-bi","paper_url":"http://arxiv.org/abs/1603.01354v5","paper_title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","code":"https://github.com/guillaumegenthial/sequence_tagging","n_code_links":25,"syntology":{"n_ran":4,"n_unverified":20,"n_samples":24,"n_pointer_only_licence":3}},{"rank_in_archive_order":12,"model":"S-LSTM","metrics":{"Accuracy":"97.55"},"uses_additional_data":false,"paper_date":"2018-05-07","paper":"/paper/sentence-state-lstm-for-text-representation","paper_url":"http://arxiv.org/abs/1805.02474v1","paper_title":"Sentence-State LSTM for Text Representation","code":"https://github.com/leuchine/S-LSTM","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"LM-LSTM-CRF","metrics":{"Accuracy":"97.53"},"uses_additional_data":false,"paper_date":"2017-09-13","paper":"/paper/empower-sequence-labeling-with-task-aware","paper_url":"http://arxiv.org/abs/1709.04109v4","paper_title":"Empower Sequence Labeling with Task-Aware Neural Language Model","code":"https://github.com/LiyuanLucasLiu/LM-LSTM-CRF","n_code_links":3,"syntology":null},{"rank_in_archive_order":14,"model":"NCRF++","metrics":{"Accuracy":"97.49"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/ncrf-an-open-source-neural-sequence-labeling","paper_url":"http://arxiv.org/abs/1806.05626v2","paper_title":"NCRF++: An Open-source Neural Sequence Labeling Toolkit","code":"https://github.com/jiesutd/PyTorchSeqLabel","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"Bi-LSTM + LMcost","metrics":{"Accuracy":"97.43"},"uses_additional_data":false,"paper_date":"2017-04-24","paper":"/paper/semi-supervised-multitask-learning-for","paper_url":"http://arxiv.org/abs/1704.07156v1","paper_title":"Semi-supervised Multitask Learning for Sequence Labeling","code":"https://github.com/marekrei/sequence-labeler","n_code_links":3,"syntology":null},{"rank_in_archive_order":16,"model":"Feed Forward","metrics":{"Accuracy":"97.4"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/supertagging-with-lstms","paper_url":"https://aclanthology.org/N16-1027","paper_title":"Supertagging With LSTMs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"Bi-LSTM","metrics":{"Accuracy":"97.36"},"uses_additional_data":false,"paper_date":"2015-08-09","paper":"/paper/finding-function-in-form-compositional-1","paper_url":"http://arxiv.org/abs/1508.02096v2","paper_title":"Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation","code":"https://github.com/wlin12/JNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"Bi-LSTM + charattn","metrics":{"Accuracy":"97.27"},"uses_additional_data":false,"paper_date":"2016-11-14","paper":"/paper/attending-to-characters-in-neural-sequence","paper_url":"http://arxiv.org/abs/1611.04361v1","paper_title":"Attending to Characters in Neural Sequence Labeling Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"Bi-LSTM","metrics":{"Accuracy":"97.22"},"uses_additional_data":false,"paper_date":"2016-04-19","paper":"/paper/multilingual-part-of-speech-tagging-with","paper_url":"http://arxiv.org/abs/1604.05529v3","paper_title":"Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss","code":"https://github.com/ilyagusev/rnnmorph","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":20,"model":"SALE","metrics":{},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/sequential-alignment-methods-for-ensemble","paper_url":"https://ieeexplore.ieee.org/abstract/document/9736558?casa_token=","paper_title":"Sequential Alignment Methods for Ensemble Part-of-Speech Tagging","code":"https://github.com/jeesu-jung/alignment_based_sequence_ensemble","n_code_links":1,"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":5,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":39,"n_samples":46,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":39,"n_samples":46,"n_pointer_only_licence":5,"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"}}}