{"url":"/sota/vietnamese-text-diacritization-on","task":{"name":"Vietnamese Text Diacritization","url":"/task/vietnamese-text-diacritization","note":null},"dataset":{"name":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","url":"/dataset/multilingual-dataset-for-training-and"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Addition of diacritics for undiacritized Vietnamese Wikipedia texts.","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":["Alpha-Word accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Alpha-Word accuracy":"higher"}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"BERT","metrics":{"Alpha-Word accuracy":"98.53"},"uses_additional_data":false,"paper_date":"2021-05-24","paper":"/paper/diacritics-restoration-using-bert-with","paper_url":"https://arxiv.org/abs/2105.11408v1","paper_title":"Diacritics Restoration using BERT with Analysis on Czech language","code":"https://github.com/ufal/bert-diacritics-restoration","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"RNN + LM","metrics":{"Alpha-Word accuracy":"97.73"},"uses_additional_data":false,"paper_date":"2018-05-01","paper":"/paper/diacritics-restoration-using-neural-networks","paper_url":"https://aclanthology.org/L18-1247","paper_title":"Diacritics Restoration Using Neural Networks","code":"https://github.com/arahusky/diacritics_restoration","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"RNN","metrics":{"Alpha-Word accuracy":"97.55"},"uses_additional_data":false,"paper_date":"2018-05-01","paper":"/paper/diacritics-restoration-using-neural-networks","paper_url":"https://aclanthology.org/L18-1247","paper_title":"Diacritics Restoration Using Neural Networks","code":"https://github.com/arahusky/diacritics_restoration","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":1,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":1,"n_samples":1,"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":1,"n_samples":1,"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"}}}