{"id":"W2051349122","doi":"10.3115/1118853.1118874","title":"Letter level learning for language independent diacritics restoration","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Romanian; Czech; Computer science; Natural language processing; Artificial intelligence; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001720523,0.00008288475,0.00007522781,0.00007445454,0.0001087495,0.0001904963,0.0003950022,0.00006340125,0.00003053233],"category_scores_gemma":[0.0001507337,0.00007134206,0.00003494056,0.0001273826,0.00001349453,0.0004980119,0.0001015432,0.0001570078,0.00002696539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000378678,"about_ca_system_score_gemma":0.000006460913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001580604,"about_ca_topic_score_gemma":0.00001060902,"domain_scores_codex":[0.9992762,0.00002805121,0.0001211917,0.0002134353,0.000180748,0.0001804249],"domain_scores_gemma":[0.9995621,0.00006862996,0.00004204447,0.0002205062,0.0000723077,0.00003438071],"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":[0.000007244356,0.0001532384,0.0004768604,0.0001283874,0.00002302247,0.00007619388,0.009204993,0.00006005966,0.05657788,0.2626861,0.1592601,0.5113459],"study_design_scores_gemma":[0.001236012,0.0004597931,0.0003156423,0.0001141599,0.00002248273,0.00007805123,0.0002422702,0.4781891,0.377158,0.03689319,0.1039348,0.001356421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001194114,0.0006633535,0.9933098,0.002889381,0.0001152218,0.0001305265,7.786711e-7,0.0006558684,0.001040958],"genre_scores_gemma":[0.4704691,0.000003143041,0.5239017,0.001753776,0.0001067325,0.00001937853,0.000002643134,0.000007400218,0.003736168],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5099895,"threshold_uncertainty_score":0.2909245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03785590327783317,"score_gpt":0.288233978363281,"score_spread":0.2503780750854478,"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."}}