{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/spelling-correction","name":"Spelling Correction","slug":"spelling-correction","description_markdown":"Spelling correction is the task of detecting and correcting spelling mistakes.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":193,"papers_with_code":52,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":1,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/github-typo-corpus","name":"GitHub Typo Corpus","full_name":"GitHub Typo Corpus","num_papers_in_archive":3},{"url":"/dataset/cscd-ime","name":"CSCD-IME","full_name":"","num_papers_in_archive":2},{"url":"/dataset/mcscset","name":"MCSCSet","full_name":"","num_papers_in_archive":2},{"url":"/dataset/viwiki-spelling","name":"Viwiki-Spelling","full_name":"Vietnamese Spelling Correction Dataset","num_papers_in_archive":1}],"subtasks":[{"url":"/task/bangla-spelling-error-correction","name":"Bangla Spelling Error Correction"}],"parent_tasks":[{"url":"/task/text-generation","name":"Text Generation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":193,"of_with_code":52,"tagged_in_all":193,"counts":{"archive_papers_tagged":193,"with_a_code_link":52,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":193,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/an-actor-critic-algorithm-for-sequence","slug":"an-actor-critic-algorithm-for-sequence","title":"An Actor-Critic Algorithm for Sequence Prediction","date":"2016-07-24","arxiv_id":"1607.07086","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/an-actor-critic-algorithm-for-sequence#ran","syntology_url":"https://syntology.ai/paper/1607.07086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.07086"}},"official":{"repos":["rizar/actor-critic-public"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/a-methodology-for-generative-spelling","slug":"a-methodology-for-generative-spelling","title":"A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages","date":"2023-08-18","arxiv_id":"2308.09435","repositories_listed":2,"syntology":null},{"url":"/paper/chinese-spelling-correction-as-rephrasing","slug":"chinese-spelling-correction-as-rephrasing","title":"Chinese Spelling Correction as Rephrasing Language Model","date":"2023-08-17","arxiv_id":"2308.08796","repositories_listed":2,"syntology":null},{"url":"/paper/an-extended-sequence-tagging-vocabulary-for","slug":"an-extended-sequence-tagging-vocabulary-for","title":"An Extended Sequence Tagging Vocabulary for Grammatical Error Correction","date":"2023-02-12","arxiv_id":"2302.05913","repositories_listed":2,"syntology":null},{"url":"/paper/tokenization-repair-in-the-presence-of","slug":"tokenization-repair-in-the-presence-of","title":"Tokenization Repair in the Presence of Spelling Errors","date":"2020-10-15","arxiv_id":"2010.07878","repositories_listed":2,"syntology":null},{"url":"/paper/robust-to-noise-models-in-natural-language","slug":"robust-to-noise-models-in-natural-language","title":"Robust to Noise Models in Natural Language Processing Tasks","date":"2019-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/monoise-modeling-noise-using-a-modular","slug":"monoise-modeling-noise-using-a-modular","title":"MoNoise: Modeling Noise Using a Modular Normalization System","date":"2017-10-10","arxiv_id":"1710.03476","repositories_listed":2,"syntology":null},{"url":"/paper/tispell-a-semi-masked-methodology-for-tibetan","slug":"tispell-a-semi-masked-methodology-for-tibetan","title":"TiSpell: A Semi-Masked Methodology for Tibetan Spelling Correction covering Multi-Level Error with Data Augmentation","date":"2025-05-12","arxiv_id":"2505.08037","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-impact-of-multimodal-features","slug":"unveiling-the-impact-of-multimodal-features","title":"Unveiling the Impact of Multimodal Features on Chinese Spelling Correction: From Analysis to Design","date":"2025-04-10","arxiv_id":"2504.07661","repositories_listed":1,"syntology":null},{"url":"/paper/a-training-free-llm-based-approach-to-general","slug":"a-training-free-llm-based-approach-to-general","title":"A Training-free LLM-based Approach to General Chinese Character Error Correction","date":"2025-02-21","arxiv_id":"2502.15266","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-character-level-understanding-in","slug":"enhancing-character-level-understanding-in","title":"Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning","date":"2024-11-26","arxiv_id":"2411.17679","repositories_listed":1,"syntology":null},{"url":"/paper/cnmbert-a-model-for-hanyu-pinyin-abbreviation","slug":"cnmbert-a-model-for-hanyu-pinyin-abbreviation","title":"CNMBERT: A Model for Converting Hanyu Pinyin Abbreviations to Chinese Characters","date":"2024-11-18","arxiv_id":"2411.11770","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-yet-effective-training-free-prompt","slug":"a-simple-yet-effective-training-free-prompt","title":"A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models","date":"2024-10-05","arxiv_id":"2410.04027","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-simple-yet-effective-training-free-prompt#ran","syntology_url":"https://syntology.ai/paper/2410.04027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04027"}},"official":{"repos":["Jacob-Zhou/simple-csc"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/edacsc-two-easy-data-augmentation-methods-for","slug":"edacsc-two-easy-data-augmentation-methods-for","title":"EdaCSC: Two Easy Data Augmentation Methods for Chinese Spelling Correction","date":"2024-09-08","arxiv_id":"2409.05105","repositories_listed":1,"syntology":null},{"url":"/paper/a-coin-has-two-sides-a-novel-detector","slug":"a-coin-has-two-sides-a-novel-detector","title":"A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction","date":"2024-09-06","arxiv_id":"2409.04150","repositories_listed":1,"syntology":null},{"url":"/paper/araspell-a-deep-learning-approach-for-arabic","slug":"araspell-a-deep-learning-approach-for-arabic","title":"AraSpell: A Deep Learning Approach for Arabic Spelling Correction","date":"2024-05-11","arxiv_id":"2405.06981","repositories_listed":1,"syntology":null},{"url":"/paper/eval-gcsc-a-new-metric-for-evaluating-chatgpt","slug":"eval-gcsc-a-new-metric-for-evaluating-chatgpt","title":"Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction","date":"2023-11-14","arxiv_id":"2311.08219","repositories_listed":1,"syntology":null},{"url":"/paper/gio-gradient-information-optimization-for","slug":"gio-gradient-information-optimization-for","title":"GIO: Gradient Information Optimization for Training Dataset Selection","date":"2023-06-20","arxiv_id":"2306.11670","repositories_listed":1,"syntology":null},{"url":"/paper/spellmapper-a-non-autoregressive-neural","slug":"spellmapper-a-non-autoregressive-neural","title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings","date":"2023-06-04","arxiv_id":"2306.02317","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-masked-language-modeling-for","slug":"rethinking-masked-language-modeling-for","title":"Rethinking Masked Language Modeling for Chinese Spelling Correction","date":"2023-05-28","arxiv_id":"2305.17721","repositories_listed":1,"syntology":null},{"url":"/paper/disentangled-phonetic-representation-for","slug":"disentangled-phonetic-representation-for","title":"Disentangled Phonetic Representation for Chinese Spelling Correction","date":"2023-05-24","arxiv_id":"2305.14783","repositories_listed":1,"syntology":null},{"url":"/paper/an-error-guided-correction-model-for-chinese","slug":"an-error-guided-correction-model-for-chinese","title":"An Error-Guided Correction Model for Chinese Spelling Error Correction","date":"2023-01-16","arxiv_id":"2301.06323","repositories_listed":1,"syntology":null},{"url":"/paper/inducing-character-level-structure-in-subword","slug":"inducing-character-level-structure-in-subword","title":"Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training","date":"2022-12-19","arxiv_id":"2212.09897","repositories_listed":1,"syntology":null},{"url":"/paper/cscd-ime-correcting-spelling-errors-generated","slug":"cscd-ime-correcting-spelling-errors-generated","title":"CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers","date":"2022-11-16","arxiv_id":"2211.08788","repositories_listed":1,"syntology":null},{"url":"/paper/mcscset-a-specialist-annotated-dataset-for","slug":"mcscset-a-specialist-annotated-dataset-for","title":"MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction","date":"2022-10-21","arxiv_id":"2210.11720","repositories_listed":1,"syntology":null},{"url":"/paper/look-ma-only-400-samples-revisiting-the","slug":"look-ma-only-400-samples-revisiting-the","title":"Look Ma, Only 400 Samples! Revisiting the Effectiveness of Automatic N-Gram Rule Generation for Spelling Normalization in Filipino","date":"2022-10-06","arxiv_id":"2210.02675","repositories_listed":1,"syntology":null},{"url":"/paper/bspell-a-cnn-blended-bert-based-bengali-spell","slug":"bspell-a-cnn-blended-bert-based-bengali-spell","title":"BSpell: A CNN-Blended BERT Based Bangla Spell Checker","date":"2022-08-20","arxiv_id":"2208.09709","repositories_listed":1,"syntology":null},{"url":"/paper/abb-bert-a-bert-model-for-disambiguating","slug":"abb-bert-a-bert-model-for-disambiguating","title":"ABB-BERT: A BERT model for disambiguating abbreviations and contractions","date":"2022-07-08","arxiv_id":"2207.04008","repositories_listed":1,"syntology":null},{"url":"/paper/craspell-a-contextual-typo-robust-approach-to","slug":"craspell-a-contextual-typo-robust-approach-to","title":"CRASpell: A Contextual Typo Robust Approach to Improve Chinese Spelling Correction","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-contextual-spelling-correction-for","slug":"towards-contextual-spelling-correction-for","title":"Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems","date":"2022-03-02","arxiv_id":"2203.00888","repositories_listed":1,"syntology":null},{"url":"/paper/varclr-variable-semantic-representation-pre","slug":"varclr-variable-semantic-representation-pre","title":"VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning","date":"2021-12-05","arxiv_id":"2112.02650","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/varclr-variable-semantic-representation-pre#ran","syntology_url":"https://syntology.ai/paper/2112.02650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02650"}},"official":{"repos":["squareslab/varclr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/plome-pre-training-with-misspelled-knowledge","slug":"plome-pre-training-with-misspelled-knowledge","title":"PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bert-defense-a-probabilistic-model-based-on","slug":"bert-defense-a-probabilistic-model-based-on","title":"BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks","date":"2021-06-02","arxiv_id":"2106.01452","repositories_listed":1,"syntology":null},{"url":"/paper/exploration-and-exploitation-two-ways-to","slug":"exploration-and-exploitation-two-ways-to","title":"Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models","date":"2021-05-31","arxiv_id":"2105.14813","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-transformer-encoders-for","slug":"hierarchical-transformer-encoders-for","title":"Hierarchical Transformer Encoders for Vietnamese Spelling Correction","date":"2021-05-28","arxiv_id":"2105.13578","repositories_listed":1,"syntology":null},{"url":"/paper/similarity-based-unsupervised-spelling","slug":"similarity-based-unsupervised-spelling","title":"Similarity-Based Unsupervised Spelling Correction Using BioWordVec: Development and Usability Study of Bacterial Culture and Antimicrobial Susceptibility Reports","date":"2021-02-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/arabisc-context-sensitive-neural-spelling","slug":"arabisc-context-sensitive-neural-spelling","title":"Arabisc: Context-Sensitive Neural Spelling Checker","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-stand-alone-neural-spelling","slug":"context-aware-stand-alone-neural-spelling","title":"Context-aware Stand-alone Neural Spelling Correction","date":"2020-11-12","arxiv_id":"2011.06642","repositories_listed":1,"syntology":null},{"url":"/paper/neuspell-a-neural-spelling-correction-toolkit","slug":"neuspell-a-neural-spelling-correction-toolkit","title":"NeuSpell: A Neural Spelling Correction Toolkit","date":"2020-10-21","arxiv_id":"2010.11085","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/neuspell-a-neural-spelling-correction-toolkit#ran","syntology_url":"https://syntology.ai/paper/2010.11085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11085"}},"official":{"repos":["neuspell/neuspell"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptable-filtering-using-hierarchical","slug":"adaptable-filtering-using-hierarchical","title":"Domain-shift Conditioning using Adaptable Filtering via Hierarchical Embeddings for Robust Chinese Spell Check","date":"2020-08-27","arxiv_id":"2008.12281","repositories_listed":1,"syntology":null},{"url":"/paper/neural-chinese-word-segmentation-as-sequence","slug":"neural-chinese-word-segmentation-as-sequence","title":"Neural Chinese Word Segmentation as Sequence to Sequence Translation","date":"2019-11-29","arxiv_id":"1911.12982","repositories_listed":1,"syntology":null},{"url":"/paper/github-typo-corpus-a-large-scale-multilingual","slug":"github-typo-corpus-a-large-scale-multilingual","title":"GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors","date":"2019-11-28","arxiv_id":"1911.12893","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/github-typo-corpus-a-large-scale-multilingual#ran","syntology_url":"https://syntology.ai/paper/1911.12893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12893"}},"official":{"repos":["mhagiwara/github-typo-corpus"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-benchmark-corpus-of-english-misspellings","slug":"a-benchmark-corpus-of-english-misspellings","title":"A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dimsim-an-accurate-chinese-phonetic","slug":"dimsim-an-accurate-chinese-phonetic","title":"DIMSIM: An Accurate Chinese Phonetic Similarity Algorithm Based on Learned High Dimensional Encoding","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/preparation-of-improved-turkish-dataset-for","slug":"preparation-of-improved-turkish-dataset-for","title":"Preparation of Improved Turkish DataSet for Sentiment Analysis in Social Media","date":"2018-01-30","arxiv_id":"1801.09975","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-context-sensitive-spelling-1","slug":"unsupervised-context-sensitive-spelling-1","title":"Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings","date":"2017-10-19","arxiv_id":"1710.07045","repositories_listed":1,"syntology":null},{"url":"/paper/systematically-adapting-machine-translation","slug":"systematically-adapting-machine-translation","title":"Systematically Adapting Machine Translation for Grammatical Error Correction","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/searnn-training-rnns-with-global-local-losses","slug":"searnn-training-rnns-with-global-local-losses","title":"SEARNN: Training RNNs with Global-Local Losses","date":"2017-06-14","arxiv_id":"1706.04499","repositories_listed":1,"syntology":null},{"url":"/paper/kyoto-university-participation-to-wat-2016","slug":"kyoto-university-participation-to-wat-2016","title":"Kyoto University Participation to WAT 2016","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/robsut-wrod-reocginiton-via-semi-character","slug":"robsut-wrod-reocginiton-via-semi-character","title":"Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network","date":"2016-08-07","arxiv_id":"1608.02214","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robsut-wrod-reocginiton-via-semi-character#ran","syntology_url":"https://syntology.ai/paper/1608.02214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.02214"}},"official":null}},{"url":"/paper/data-driven-spelling-correction-using","slug":"data-driven-spelling-correction-using","title":"Data-Driven Spelling Correction using Weighted Finite-State Methods","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-generalized-language-model-as-the-1","slug":"a-generalized-language-model-as-the-1","title":"A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser Ney Smoothing","date":"2014-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"2505-11008","title":"Reconstructing Syllable Sequences in Abugida Scripts with Incomplete Inputs","date":"2025-05-16","arxiv_id":"2505.11008","repositories_listed":0,"syntology":null},{"url":null,"slug":"cec-zero-chinese-error-correction-solution","title":"CEC-Zero: Chinese Error Correction Solution Based on LLM","date":"2025-05-14","arxiv_id":"2505.09082","repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-spelling-correction-a-comprehensive","title":"Chinese Spelling Correction: A Comprehensive Survey of Progress, Challenges, and Opportunities","date":"2025-02-17","arxiv_id":"2502.11508","repositories_listed":0,"syntology":null},{"url":null,"slug":"integration-of-llm-quality-assurance-into-an","title":"Integration of LLM Quality Assurance into an NLG System","date":"2025-01-27","arxiv_id":"2501.16078","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-framework-for-semantic","title":"A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques","date":"2025-01-24","arxiv_id":"2501.14288","repositories_listed":0,"syntology":null},{"url":null,"slug":"research-on-domain-specific-chinese-spelling","title":"Research on Domain-Specific Chinese Spelling Correction Method Based on Plugin Extension Modules","date":"2024-11-15","arxiv_id":"2411.09884","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-importance-of-homophones-spelling","title":"A Survey on Importance of Homophones Spelling Correction Model for Khmer Authors","date":"2024-11-11","arxiv_id":"2411.10477","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-spelling-correction-for-e","title":"Retrieval Augmented Spelling Correction for E-Commerce Applications","date":"2024-10-15","arxiv_id":"2410.11655","repositories_listed":0,"syntology":null},{"url":null,"slug":"ringgesture-a-ring-based-mid-air-gesture","title":"RingGesture: A Ring-Based Mid-Air Gesture Typing System Powered by a Deep-Learning Word Prediction Framework","date":"2024-10-08","arxiv_id":"2410.18100","repositories_listed":0,"syntology":null},{"url":null,"slug":"spelling-correction-through-rewriting-of-non","title":"Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices","date":"2024-09-24","arxiv_id":"2409.16469","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-quality-of-persian-clinical","title":"Improving the quality of Persian clinical text with a novel spelling correction system","date":"2024-08-07","arxiv_id":"2408.03622","repositories_listed":0,"syntology":null},{"url":null,"slug":"refining-corpora-from-a-model-calibration","title":"Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction","date":"2024-07-22","arxiv_id":"2407.15498","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-real-word-error-correction-in","title":"Automatic Real-word Error Correction in Persian Text","date":"2024-07-20","arxiv_id":"2407.14795","repositories_listed":0,"syntology":null},{"url":null,"slug":"percore-a-deep-learning-based-framework-for","title":"PERCORE: A Deep Learning-Based Framework for Persian Spelling Correction with Phonetic Analysis","date":"2024-07-20","arxiv_id":"2407.14789","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-combination-of-bert-and-transformer-for","title":"A Combination of BERT and Transformer for Vietnamese Spelling Correction","date":"2024-05-04","arxiv_id":"2405.02573","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-spelling-correction-with-language","title":"Contextual Spelling Correction with Language Model for Low-resource Setting","date":"2024-04-28","arxiv_id":"2404.18072","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-simultaneous-named","title":"Large Language Models for Simultaneous Named Entity Extraction and Spelling Correction","date":"2024-03-01","arxiv_id":"2403.00528","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-catastrophic-forgetting-in-multi","title":"Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Framework","date":"2024-02-18","arxiv_id":"2402.11422","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-teacher-distillation-for-multilingual","title":"Multi-teacher Distillation for Multilingual Spelling Correction","date":"2023-11-20","arxiv_id":"2311.11518","repositories_listed":0,"syntology":null},{"url":null,"slug":"sampling-and-ranking-for-digital-ink","title":"Sampling and Ranking for Digital Ink Generation on a tight computational budget","date":"2023-06-02","arxiv_id":"2306.03103","repositories_listed":0,"syntology":null},{"url":null,"slug":"persian-typographical-error-type-detection","title":"Persian Typographical Error Type Detection Using Deep Neural Networks on Algorithmically-Generated Misspellings","date":"2023-05-19","arxiv_id":"2305.11731","repositories_listed":0,"syntology":null},{"url":null,"slug":"beqi-revitalize-the-senegalese-wolof-language","title":"Beqi: Revitalize the Senegalese Wolof Language with a Robust Spelling Corrector","date":"2023-05-15","arxiv_id":"2305.08518","repositories_listed":0,"syntology":null},{"url":null,"slug":"cleansing-jewel-a-neural-spelling-correction","title":"Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts","date":"2023-04-07","arxiv_id":"2304.03427","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-contextual-spelling-correction-by","title":"Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation","date":"2023-02-22","arxiv_id":"2302.11192","repositories_listed":0,"syntology":null},{"url":null,"slug":"correcting-real-word-spelling-errors-a-new","title":"Correcting Real-Word Spelling Errors: A New Hybrid Approach","date":"2023-02-09","arxiv_id":"2302.06407","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-word-error-correction-with-trigrams","title":"Real-Word Error Correction with Trigrams: Correcting Multiple Errors in a Sentence","date":"2023-02-07","arxiv_id":"2302.04096","repositories_listed":0,"syntology":null},{"url":null,"slug":"diacorrect-end-to-end-error-correction-for","title":"DiaCorrect: End-to-end error correction for speaker diarization","date":"2022-10-31","arxiv_id":"2210.17189","repositories_listed":0,"syntology":null},{"url":null,"slug":"english-language-spelling-correction-as-an","title":"English Language Spelling Correction as an Information Retrieval Task Using Wikipedia Search Statistics","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mdcspell-a-multi-task-detector-corrector","title":"MDCSpell: A Multi-task Detector-Corrector Framework for Chinese Spelling Correction","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spelling-correction-using-phonetics-in-e","title":"Spelling Correction using Phonetics in E-commerce Search","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"restricted-forensic-levenshtein-distance","title":"A New String Edit Distance and Applications","date":"2022-03-11","arxiv_id":"2203.06138","repositories_listed":0,"syntology":null},{"url":null,"slug":"inkorrect-online-handwriting-spelling","title":"Inkorrect: Online Handwriting Spelling Correction","date":"2022-02-28","arxiv_id":"2202.13794","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-random-perturbations-to-mitigate","title":"Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models","date":"2022-02-11","arxiv_id":"2202.05758","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-influence-of-regional-pronunciation","title":"The Influence of Regional Pronunciation Variation on Children’s Spelling and the Potential Benefits of Accent Adapted Spellcheckers","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vsec-transformer-based-model-for-vietnamese","title":"VSEC: Transformer-based Model for Vietnamese Spelling Correction","date":"2021-11-01","arxiv_id":"2111.00640","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-abbreviation-expansion-in-context","title":"Structured abbreviation expansion in context","date":"2021-10-04","arxiv_id":"2110.01140","repositories_listed":0,"syntology":null},{"url":null,"slug":"spelling-correction-for-russian-a-comparative","title":"Spelling Correction for Russian: A Comparative Study of Datasets and Methods","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-light-weight-contextual-spelling-correction","title":"A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems","date":"2021-08-17","arxiv_id":"2108.07493","repositories_listed":0,"syntology":null},{"url":null,"slug":"correcting-arabic-soft-spelling-mistakes","title":"Correcting Arabic Soft Spelling Mistakes using BiLSTM-based Machine Learning","date":"2021-08-02","arxiv_id":"2108.01141","repositories_listed":0,"syntology":null},{"url":"/paper/spelling-correction-with-denoising","slug":"spelling-correction-with-denoising","title":"Spelling Correction with Denoising Transformer","date":"2021-05-12","arxiv_id":"2105.05977","repositories_listed":0,"syntology":null},{"url":null,"slug":"spell-correction-for-azerbaijani-language","title":"Spell Correction for Azerbaijani Language using Deep Neural Networks","date":"2021-02-05","arxiv_id":"2102.03218","repositories_listed":0,"syntology":null},{"url":null,"slug":"misspelling-correction-with-pre-trained","title":"Misspelling Correction with Pre-trained Contextual Language Model","date":"2021-01-08","arxiv_id":"2101.03204","repositories_listed":0,"syntology":null},{"url":null,"slug":"vartani-spellcheck-automatic-context","title":"Vartani Spellcheck -- Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance","date":"2020-12-14","arxiv_id":"2012.07652","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-interactive-knowledge-base","title":"Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages","date":"2020-10-20","arxiv_id":"2010.10472","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-spelling-correction-corpus-for-multiple","title":"A Spelling Correction Corpus for Multiple Arabic Dialects","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-in-depth-comparison-of-14-spelling","title":"An In-Depth Comparison of 14 Spelling Correction Tools on a Common Benchmark","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"disambiguating-confusion-sets-as-an-aid-for","title":"Disambiguating Confusion Sets as an Aid for Dyslexic Spelling","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-spelling-correction-for-clinical","title":"Automated Spelling Correction for Clinical Text Mining in Russian","date":"2020-04-10","arxiv_id":"2004.04987","repositories_listed":0,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/task/spelling-correction/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/spelling-correction/papers/2","json":"/task/spelling-correction/papers/2.json","rows":93},{"order":"ran","page":1,"of":1,"url":"/task/spelling-correction/papers/ran/1","json":"/task/spelling-correction/papers/ran/1.json","rows":5}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"8134afef66304e9dad7789001b3d581123b12b1806c832eb8cc4df481eb5484e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}