{"id":"W4293863327","doi":"10.1109/siu55565.2022.9864878","title":"Neural Machine Translation Approaches for Post-OCR Text Processing","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Automatic summarization; Computer science; Optical character recognition; Machine translation; Artificial intelligence; Natural language processing; Text recognition; Process (computing); Speech recognition; Document processing; Error detection and correction; Translation (biology); Intelligent word recognition; Pattern recognition (psychology); Information extraction; Character recognition; Image (mathematics); Intelligent character recognition","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006844807,0.0002633152,0.0002645277,0.0003047246,0.00324047,0.0006117896,0.002293649,0.00007519637,0.0000566876],"category_scores_gemma":[0.00001392313,0.0002868113,0.00008571948,0.001033116,0.0002564091,0.0008206125,0.0007153061,0.0005366689,0.000004622806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007474861,"about_ca_system_score_gemma":0.0003819937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003047245,"about_ca_topic_score_gemma":0.00002455939,"domain_scores_codex":[0.9979052,0.0002243684,0.0005296975,0.0006530081,0.0003480686,0.0003396498],"domain_scores_gemma":[0.9977339,0.0002238152,0.0003525854,0.001130997,0.0004349091,0.0001237997],"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":[0.00001190915,0.000224393,0.00003248926,0.00008225908,0.000009794846,1.631026e-7,0.001142537,0.00004662665,0.001074908,0.01878958,0.0000609473,0.9785244],"study_design_scores_gemma":[0.00040637,0.0001527701,0.00009801963,0.00003117601,0.00004294089,0.00004615435,0.00115883,0.9509996,0.0003782321,0.01605052,0.03021314,0.0004223062],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003227727,0.007717294,0.9791592,0.008343659,0.00001286528,0.001508394,0.0001196371,0.000612997,0.002203198],"genre_scores_gemma":[0.853827,0.0001243432,0.1369501,0.0004168846,0.00002695013,0.008004448,0.0004463873,0.00002814215,0.0001757916],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9781021,"threshold_uncertainty_score":0.9999584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07876931332849635,"score_gpt":0.2935847599729343,"score_spread":0.214815446644438,"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."}}