{"url":"/sota/document-classification-on-reuters-21578","task":{"name":"Document Classification","url":"/task/document-classification","note":null},"dataset":{"name":"Reuters-21578","url":"/dataset/reuters-21578"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Document Classification** is a procedure of assigning one or more labels to a document from a predetermined set of labels.\n\n\n<span class=\"description-source\">Source: [Long-length Legal Document Classification ](https://arxiv.org/abs/1912.06905)</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":["Accuracy","F1"],"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","F1":"higher"}},"counts":{"rows":8,"rows_with_code":8,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ApproxRepSet","metrics":{"Accuracy":"97.17"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/rep-the-set-neural-networks-for-learning-set","paper_url":"https://arxiv.org/abs/1904.01962v2","paper_title":"Rep the Set: Neural Networks for Learning Set Representations","code":"https://github.com/giannisnik/repset","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"REL-RWMD k-NN","metrics":{"Accuracy":"95.61"},"uses_additional_data":false,"paper_date":"2019-12-01","paper":"/paper/speeding-up-word-movers-distance-and-its","paper_url":"https://arxiv.org/abs/1912.00509v2","paper_title":"Speeding up Word Mover's Distance and its variants via properties of distances between embeddings","code":"https://github.com/matwerner/fast-wmd","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Orthogonalized Soft VSM","metrics":{"Accuracy":"92.65"},"uses_additional_data":false,"paper_date":"2020-03-10","paper":"/paper/text-classification-with-word-embedding","paper_url":"https://arxiv.org/abs/2003.05019v1","paper_title":"Text classification with word embedding regularization and soft similarity measure","code":"https://github.com/MIR-MU/regularized-embeddings","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"MAGNET","metrics":{"F1":"89.9"},"uses_additional_data":false,"paper_date":"2020-02-24","paper":"/paper/magnet-multi-label-text-classification-using","paper_url":"https://www.scitepress.org/PublicationsDetail.aspx?ID=siCYSzSoEx0=&t=1","paper_title":"MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network","code":"https://github.com/adrinta/MAGNET","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"VLAWE","metrics":{"F1":"89.3"},"uses_additional_data":false,"paper_date":"2019-02-23","paper":"/paper/vector-of-locally-aggregated-word-embeddings","paper_url":"https://arxiv.org/abs/1902.08850v3","paper_title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation","code":"https://github.com/raduionescu/vlawe-boswe","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"KD-LSTMreg","metrics":{"F1":"88.9"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/docbert-bert-for-document-classification","paper_url":"https://arxiv.org/abs/1904.08398v3","paper_title":"DocBERT: BERT for Document Classification","code":"https://github.com/castorini/hedwig","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"LSTM-reg (single model)","metrics":{"F1":"87.0"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/rethinking-complex-neural-network","paper_url":"https://aclanthology.org/N19-1408","paper_title":"Rethinking Complex Neural Network Architectures for Document Classification","code":"https://github.com/castorini/hedwig","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"SCDV-MS","metrics":{"F1":"82.71"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/improving-document-classification-with-multi","paper_url":"https://arxiv.org/abs/1911.07918v1","paper_title":"Improving Document Classification with Multi-Sense Embeddings","code":"https://github.com/vgupta123/SCDV-MS","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 6,264 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":2,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":15,"n_samples":15,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":15,"n_samples":15,"n_pointer_only_licence":0,"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"}}}