{"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/optical-character-recognition/papers/12","list_of":"/task/optical-character-recognition","task":"Optical Character Recognition (OCR)","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":12,"pages_in_order":13,"rows_per_page":100,"rows":[1101,1200],"of":1243,"counts":{"archive_papers_tagged":1243,"with_a_code_link":462,"where_syntology_ran_a_sample":76,"not_listed_spam_title":0,"listed":1243,"listed_where_code_ran":76,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":64,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":64,"listed_every_run_a_failure_of_syntologys_instrument":12,"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"},"first_page":"/task/optical-character-recognition","prev":"/task/optical-character-recognition/papers/11","next":"/task/optical-character-recognition/papers/13","papers":[{"url":null,"slug":"tagging-named-entities-in-19th-century-and","title":"Tagging Named Entities in 19th Century and Modern Finnish Newspaper Material with a Finnish Semantic Tagger","date":"2017-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-making-of-the-royal-society-corpus","title":"The Making of the Royal Society Corpus","date":"2017-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-compositor-attribution-in-the-first","title":"Automatic Compositor Attribution in the First Folio of Shakespeare","date":"2017-04-25","arxiv_id":"1704.07875","repositories_listed":0,"syntology":null},{"url":null,"slug":"scatteract-automated-extraction-of-data-from","title":"Scatteract: Automated extraction of data from scatter plots","date":"2017-04-21","arxiv_id":"1704.06687","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocrapose-ii-an-ocr-based-indoor-positioning","title":"OCRAPOSE II: An OCR-based indoor positioning system using mobile phone images","date":"2017-04-19","arxiv_id":"1704.05591","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-search-space-reduction-for-spell","title":"Effective search space reduction for spell correction using character neural embeddings","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"important-new-developments-in-arabographic","title":"Important New Developments in Arabographic Optical Character Recognition (OCR)","date":"2017-03-28","arxiv_id":"1703.09550","repositories_listed":0,"syntology":null},{"url":null,"slug":"content-based-similar-document-image","title":"Content-based similar document image retrieval using fusion of CNN features","date":"2017-03-23","arxiv_id":"1703.08013","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-holistic-approach-for-optimizing-dsp-block","title":"A Holistic Approach for Optimizing DSP Block Utilization of a CNN implementation on FPGA","date":"2017-03-21","arxiv_id":"1703.09779","repositories_listed":0,"syntology":null},{"url":"/paper/twitter100k-a-real-world-dataset-for-weakly","slug":"twitter100k-a-real-world-dataset-for-weakly","title":"Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval","date":"2017-03-20","arxiv_id":"1703.06618","repositories_listed":0,"syntology":null},{"url":null,"slug":"endangered-data-for-endangered-languages","title":"Endangered Data for Endangered Languages: Digitizing Print dictionaries","date":"2017-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-independent-single-document-image","title":"Language Independent Single Document Image Super-Resolution using CNN for improved recognition","date":"2017-01-30","arxiv_id":"1701.08835","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-decomposition-of-bangla-printed-text","title":"Document Decomposition of Bangla Printed Text","date":"2017-01-27","arxiv_id":"1701.08706","repositories_listed":0,"syntology":null},{"url":null,"slug":"profiling-of-ocred-historical-texts-revisited","title":"Profiling of OCR'ed Historical Texts Revisited","date":"2017-01-19","arxiv_id":"1701.05377","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognition-of-text-image-using-multilayer","title":"Recognition of Text Image Using Multilayer Perceptron","date":"2016-12-02","arxiv_id":"1612.00625","repositories_listed":0,"syntology":null},{"url":null,"slug":"align-me-a-framework-to-generate-parallel","title":"Align Me: A framework to generate Parallel Corpus Using OCRs and Bilingual Dictionaries","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-text-reuse-in-french-medical","title":"Detection of Text Reuse in French Medical Corpora","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"implementation-of-a-workflow-management","title":"Implementation of a Workflow Management System for Non-Expert Users","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-optical-character-recognition-and","title":"Integrating Optical Character Recognition and Machine Translation of Historical Documents","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"papago-a-machine-translation-service-with","title":"papago: A Machine Translation Service with Word Sense Disambiguation and Currency Conversion","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"providing-and-analyzing-nlp-terms-for-our","title":"Providing and Analyzing NLP Terms for our Community","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-learning-for-ocr-text-correction","title":"Statistical Learning for OCR Text Correction","date":"2016-11-21","arxiv_id":"1611.06950","repositories_listed":0,"syntology":null},{"url":null,"slug":"old-content-and-modern-tools-searching-named","title":"Old Content and Modern Tools - Searching Named Entities in a Finnish OCRed Historical Newspaper Collection 1771-1910","date":"2016-11-09","arxiv_id":"1611.02839","repositories_listed":0,"syntology":null},{"url":null,"slug":"chineseenglish-mixed-character-segmentation","title":"Chinese/English mixed Character Segmentation as Semantic Segmentation","date":"2016-11-07","arxiv_id":"1611.01982","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-ocr-error-detection-and","title":"Low-resource OCR error detection and correction in French Clinical Texts","date":"2016-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"still-not-there-comparing-traditional","title":"Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks","date":"2016-10-25","arxiv_id":"1610.07796","repositories_listed":0,"syntology":null},{"url":null,"slug":"proposal-for-automatic-license-and-number","title":"Proposal for Automatic License and Number Plate Recognition System for Vehicle Identification","date":"2016-10-09","arxiv_id":"1610.03341","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-a-robust-framework-for-information-1","title":"OCR++: A Robust Framework For Information Extraction from Scholarly Articles","date":"2016-09-23","arxiv_id":"1609.06423","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-of-historical-printings-with-an","title":"OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus","date":"2016-08-06","arxiv_id":"1608.02153","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-phonology-and-morphology-for-the","title":"Combining Phonology and Morphology for the Normalization of Historical Texts","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-inter-annotator-agreement-on","title":"Evaluating Inter-Annotator Agreement on Historical Spelling Normalization","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"n-gram-language-models-for-massively-parallel","title":"N-gram language models for massively parallel devices","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pynini-a-python-library-for-weighted-finite","title":"Pynini: A Python library for weighted finite-state grammar compilation","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-automated-annotation-of-page-based","title":"Semi-automated annotation of page-based documents within the Genre and Multimodality framework","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-morph-segmentation-and","title":"Unsupervised morph segmentation and statistical language models for vocabulary expansion","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/benchmark-for-license-plate-character","slug":"benchmark-for-license-plate-character","title":"Benchmark for License Plate Character Segmentation","date":"2016-07-11","arxiv_id":"1607.02937","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-neural-networks-and-fuzzy-logic","title":"Artificial neural networks and fuzzy logic for recognizing alphabet characters and mathematical symbols","date":"2016-07-06","arxiv_id":"1607.02028","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-many-faces-can-be-recognized-performance","title":"How many faces can be recognized? Performance extrapolation for multi-class classification","date":"2016-06-16","arxiv_id":"1606.05228","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generic-method-for-automatic-ground-truth","title":"A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents","date":"2016-05-04","arxiv_id":"1605.01189","repositories_listed":0,"syntology":null},{"url":null,"slug":"1-million-captioned-dutch-newspaper-images","title":"1 Million Captioned Dutch Newspaper Images","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crowdsourcing-an-ocr-gold-standard-for-a","title":"Crowdsourcing an OCR Gold Standard for a German and French Heritage Corpus","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-weighted-language-lexicons-from","title":"Extracting Weighted Language Lexicons from Wikipedia","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-lexical-quality-of-a-historical","title":"Measuring Lexical Quality of a Historical Finnish Newspaper Collection ― Analysis of Garbled OCR Data with Basic Language Technology Tools and Means","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-post-correction-evaluation-of-early-dutch","title":"OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/opensubtitles2016-extracting-large-parallel","slug":"opensubtitles2016-extracting-large-parallel","title":"OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"training-quality-assessment-of-an-optical","title":"Training \\& Quality Assessment of an Optical Character Recognition Model for Northern Haida","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-smt-for-ocr-error-correction-of","title":"Using SMT for OCR Error Correction of Historical Texts","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-error-correction-using-character","title":"OCR Error Correction Using Character Correction and Feature-Based Word Classification","date":"2016-04-21","arxiv_id":"1604.06225","repositories_listed":0,"syntology":null},{"url":null,"slug":"overlay-text-extraction-from-tv-news","title":"Overlay Text Extraction From TV News Broadcast","date":"2016-04-02","arxiv_id":"1604.00470","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-recurrent-nets-with-attention","title":"Recursive Recurrent Nets with Attention Modeling for OCR in the Wild","date":"2016-03-09","arxiv_id":"1603.03101","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-constrained-structured-prediction","title":"Resource Constrained Structured Prediction","date":"2016-02-28","arxiv_id":"1602.08761","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-cleaning-for-xml-electronic-dictionaries","title":"Data Cleaning for XML Electronic Dictionaries via Statistical Anomaly Detection","date":"2016-02-25","arxiv_id":"1602.07807","repositories_listed":0,"syntology":null},{"url":null,"slug":"font-identification-in-historical-documents","title":"Font Identification in Historical Documents Using Active Learning","date":"2016-01-27","arxiv_id":"1601.07252","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-anagrammed-texts-written-in-an","title":"Decoding Anagrammed Texts Written in an Unknown Language and Script","date":"2016-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-visual-and-logical-character","title":"Comparison of Visual and Logical Character Segmentation in Tesseract OCR Language Data for Indic Writing Scripts","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-names-in-trove-named-entity","title":"Finding Names in Trove: Named Entity Recognition for Australian Historical Newspapers","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-learning-for-optical","title":"Sequence to Sequence Learning for Optical Character Recognition","date":"2015-11-13","arxiv_id":"1511.04176","repositories_listed":0,"syntology":null},{"url":null,"slug":"directional-global-three-part-image","title":"Directional Global Three-part Image Decomposition","date":"2015-10-06","arxiv_id":"1510.01490","repositories_listed":0,"syntology":null},{"url":null,"slug":"telugu-ocr-framework-using-deep-learning","title":"Telugu OCR Framework using Deep Learning","date":"2015-09-20","arxiv_id":"1509.05962","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-accuracy-improvement-on-document-images","title":"OCR accuracy improvement on document images through a novel pre-processing approach","date":"2015-09-11","arxiv_id":"1509.03456","repositories_listed":0,"syntology":null},{"url":null,"slug":"danproof-pedagogical-spell-and-grammar","title":"DanProof: Pedagogical Spell and Grammar Checking for Danish","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"is-it-possible-to-recover-personal-health","title":"Is it possible to recover personal health information from an automatically de-identified corpus of French EHRs?","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-machine-translation-improvement","title":"Statistical Machine Translation Improvement based on Phrase Selection","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-stability-over-noisy-sources","title":"Topic Stability over Noisy Sources","date":"2015-08-05","arxiv_id":"1508.01067","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-linked-data-model-for-multimodal-sentiment","title":"A Linked Data Model for Multimodal Sentiment and Emotion Analysis","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-preliminary-study-on-similarity-preserving","title":"A preliminary study on similarity-preserving digital book identifiers","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sahsohqalb-2015-shared-task-a-rule-based","title":"SAHSOH@QALB-2015 Shared Task: A Rule-Based Correction Method of Common Arabic Native and Non-Native Speakers' Errors","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"techlimedqalb-shared-task-2015-a-hybrid","title":"TECHLIMED@QALB-Shared Task 2015: a hybrid Arabic Error Correction System","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"license-plate-recognition-system-based-on","title":"License Plate Recognition System Based on Color Coding Of License Plates","date":"2015-06-08","arxiv_id":"1506.03128","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-optical-character-recognition-a","title":"Boosting Optical Character Recognition: A Super-Resolution Approach","date":"2015-06-07","arxiv_id":"1506.02211","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-translation-of-a-literary-work-a","title":"Automated Translation of a Literary Work: A Pilot Study","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-code-switching-for-multilingual","title":"Unsupervised Code-Switching for Multilingual Historical Document Transcription","date":"2015-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"squibs-spelling-error-patterns-in-brazilian","title":"Squibs: Spelling Error Patterns in Brazilian Portuguese","date":"2015-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularization-and-kernelization-of-the","title":"Regularization and Kernelization of the Maximin Correlation Approach","date":"2015-02-21","arxiv_id":"1502.06105","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-sindhi-related-and-arabic-script","title":"A Study of Sindhi Related and Arabic Script Adapted languages Recognition","date":"2014-12-13","arxiv_id":"1412.4217","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-modern-optical-character","title":"A survey of modern optical character recognition techniques","date":"2014-12-13","arxiv_id":"1412.4183","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multiple-tasks-in-parallel-with-a","title":"Learning Multiple Tasks in Parallel with a Shared Annotator","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-media-retrieval-from-non","title":"Efficient Media Retrieval from Non-Cooperative Queries","date":"2014-11-19","arxiv_id":"1411.5307","repositories_listed":0,"syntology":null},{"url":null,"slug":"optical-character-recognition-using-k-nearest","title":"Optical Character Recognition, Using K-Nearest Neighbors","date":"2014-11-05","arxiv_id":"1411.1442","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-and-automated-translation-for-the","title":"OCR and Automated Translation for the Navigation of non-English Handsets: A Feasibility Study with Arabic","date":"2014-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-random-forest-system-combination-approach","title":"A random forest system combination approach for error detection in digital dictionaries","date":"2014-10-30","arxiv_id":"1410.8553","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-captchas-security-using-gaussian-blur","title":"Improve CAPTCHA's Security Using Gaussian Blur Filter","date":"2014-10-16","arxiv_id":"1410.4441","repositories_listed":0,"syntology":null},{"url":null,"slug":"autocorrection-of-arabic-common-errors-for","title":"Autocorrection of arabic common errors for large text corpus","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"balanced-korean-word-spacing-with-structural","title":"Balanced Korean Word Spacing with Structural SVM","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cmuqqalb-2014-an-smt-based-system-for","title":"CMUQ@QALB-2014: An SMT-based System for Automatic Arabic Error Correction","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"techlimed-system-description-for-the-shared","title":"TECHLIMED system description for the Shared Task on Automatic Arabic Error Correction","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bypassing-captcha-by-machine-a-proof-for","title":"Bypassing Captcha By Machine A Proof For Passing The Turing Test","date":"2014-09-03","arxiv_id":"1409.0925","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-substitution-ciphers-with-combined","title":"Solving Substitution Ciphers with Combined Language Models","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ticclops-text-induced-corpus-clean-up-as","title":"TICCLops: Text-Induced Corpus Clean-up as online processing system","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bambara-and-maninka-manding-languages-written","title":"Bambara and Maninka Manding Languages Written Corpora Project (``Projet des corpus \\'ecrits des langues manding : le bambara, le maninka'') [in French]","date":"2014-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"named-entity-recognition-and-correction-in","title":"Named Entity Recognition and Correction in OCRized Corpora (D\\'etection et correction automatique d'entit\\'es nomm\\'ees dans des corpus OCRis\\'es) [in French]","date":"2014-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-handwritten-modi-character","title":"Offline Handwritten MODI Character Recognition Using HU, Zernike Moments and Zoning","date":"2014-06-24","arxiv_id":"1406.6140","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-typesetting-models-for-historical","title":"Improved Typesetting Models for Historical OCR","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-ensembles-of-structured-prediction","title":"Learning Ensembles of Structured Prediction Rules","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-morphology-based-vocabulary","title":"Unsupervised Morphology-Based Vocabulary Expansion","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"amazigh-verb-conjugator","title":"Amazigh Verb Conjugator","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"construction-and-annotation-of-a-french","title":"Construction and Annotation of a French Folkstale Corpus","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"corpus-of-19th-century-czech-texts-problems","title":"Corpus of 19th-century Czech Texts: Problems and Solutions","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"flelex-a-graded-lexical-resource-for-french","title":"FLELex: a graded lexical resource for French foreign learners","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"open-philology-at-the-university-of-leipzig","title":"Open Philology at the University of Leipzig","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"3fcacaad02cb52bb82e9773475fcd3fcc825f7dee0979f2649fbb61d0bb725c4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}