{"id":"W4395463230","doi":"10.18280/isi.290223","title":"Automatic Hindi OCR Error Correction Using MLM-BERT","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hindi; Computer science; Natural language processing; Artificial intelligence; Error detection and correction; Speech recognition; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008731127,0.002218326,0.001139966,0.001901966,0.0006491275,0.001014835,0.002104057,0.001107011,0.003227553],"category_scores_gemma":[0.002860405,0.0004635261,0.001041671,0.0009622964,0.0003807335,0.001409158,0.001145328,0.001223544,0.004557844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009151184,"about_ca_system_score_gemma":0.001232161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009176318,"about_ca_topic_score_gemma":0.01559852,"domain_scores_codex":[0.9988402,0.0001044384,0.00007780413,0.0003383848,0.0005271295,0.0001121709],"domain_scores_gemma":[0.998066,0.000300872,0.0002483474,0.000483937,0.0008527133,0.00004820884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006413427,0.0002208444,0.002847982,0.0003611925,0.0001243121,0.0004001539,0.0001726653,0.0668966,0.09040106,0.00130388,0.01792129,0.8187086],"study_design_scores_gemma":[0.00002296225,0.0001795101,0.001984568,0.0000332676,0.00005073501,0.0003887655,0.00005806726,0.8649433,0.1209149,0.0008121434,0.0105445,0.00006721629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07455739,0.002118549,0.8282186,0.0004330884,0.0006923051,0.0004214564,0.001960571,0.08765662,0.003941364],"genre_scores_gemma":[0.4430543,0.0008358289,0.5318391,0.0003594588,0.0001518175,0.000266923,0.00543753,0.002105074,0.01594997],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009176318,"threshold_uncertainty_score":0.01824582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03190194894866177,"score_gpt":0.2796448416792766,"score_spread":0.2477428927306148,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}