{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/diacritics-restoration-using-bert-with","title":"Diacritics Restoration using BERT with Analysis on Czech language","arxiv_id":"2105.11408","date":"2021-05-24","proceeding":null,"authors":["Jakub Náplava","Milan Straka","Jana Straková"],"abstract":"We propose a new architecture for diacritics restoration based on contextualized embeddings, namely BERT, and we evaluate it on 12 languages with diacritics. Furthermore, we conduct a detailed error analysis on Czech, a morphologically rich language with a high level of diacritization. Notably, we manually annotate all mispredictions, showing that roughly 44% of them are actually not errors, but either plausible variants (19%), or the system corrections of erroneous data (25%). Finally, we categorize the real errors in detail. We release the code at https://github.com/ufal/bert-diacritics-restoration.","url_abs":"https://arxiv.org/abs/2105.11408v1","url_pdf":"https://arxiv.org/pdf/2105.11408v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"diacritics-restoration-using-bert-with","repo_url":"https://github.com/ufal/bert-diacritics-restoration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"croatian-text-diacritization","task_name":"Croatian Text Diacritization"},{"task_slug":"czech-text-diacritization","task_name":"Czech Text Diacritization"},{"task_slug":"french-text-diacritization","task_name":"French Text Diacritization"},{"task_slug":"hungarian-text-diacritization","task_name":"Hungarian Text Diacritization"},{"task_slug":"irish-text-diacritization","task_name":"Irish Text Diacritization"},{"task_slug":"latvian-text-diacritization","task_name":"Latvian Text Diacritization"},{"task_slug":"polish-text-diacritization","task_name":"Polish Text Diacritization"},{"task_slug":"romanian-text-diacritization","task_name":"Romanian Text Diacritization"},{"task_slug":"slovak-text-diacritization","task_name":"Slovak Text Diacritization"},{"task_slug":"spanish-text-diacritization","task_name":"Spanish Text Diacritization"},{"task_slug":"turkish-text-diacritization","task_name":"Turkish Text Diacritization"},{"task_slug":"vietnamese-text-diacritization","task_name":"Vietnamese Text Diacritization"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/croatian-text-diacritization-on-multilingual","task":"Croatian Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"99.73"},"uses_additional_data":false},{"leaderboard":"/sota/czech-text-diacritization-on-multilingual","task":"Czech Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":3,"metrics":{"Alpha-Word accuracy":"99.22"},"uses_additional_data":false},{"leaderboard":"/sota/french-text-diacritization-on-multilingual","task":"French Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"99.71"},"uses_additional_data":false},{"leaderboard":"/sota/hungarian-text-diacritization-on-multilingual","task":"Hungarian Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"99.41"},"uses_additional_data":false},{"leaderboard":"/sota/irish-text-diacritization-on-multilingual","task":"Irish Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"98.88"},"uses_additional_data":false},{"leaderboard":"/sota/latvian-text-diacritization-on-multilingual","task":"Latvian Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"98.63"},"uses_additional_data":false},{"leaderboard":"/sota/polish-text-diacritization-on-multilingual","task":"Polish Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"99.66"},"uses_additional_data":false},{"leaderboard":"/sota/romanian-text-diacritization-on-multilingual","task":"Romanian Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"98.64"},"uses_additional_data":false},{"leaderboard":"/sota/slovak-text-diacritization-on-multilingual","task":"Slovak Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"99.32"},"uses_additional_data":false},{"leaderboard":"/sota/spanish-text-diacritization-on-multilingual","task":"Spanish Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"99.62"},"uses_additional_data":false},{"leaderboard":"/sota/turkish-text-diacritization-on-multilingual","task":"Turkish Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":1,"metrics":{"Alpha-Word accuracy":"98.95"},"uses_additional_data":false},{"leaderboard":"/sota/vietnamese-text-diacritization-on","task":"Vietnamese Text Diacritization","dataset":"Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems","model":"BERT","rank_in_archive_order":1,"of":3,"metrics":{"Alpha-Word accuracy":"98.53"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.11408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11408"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ufal/bert-diacritics-restoration","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d0f4321974e245c0","entry":"read_examples_from_disk","repo":"ufal/bert-diacritics-restoration","repo_kind":"official","path":"utils_diacritization.py","file_url":"https://github.com/ufal/bert-diacritics-restoration/blob/HEAD/utils_diacritization.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0f4321974e245c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}