{"id":"W3006280404","doi":"10.23977/isspj.2020.51001","title":"The First Azeri (Azerbaijani) Language Next Word Predictor","year":2020,"lang":"en","type":"article","venue":"Information Systems and Signal Processing Journal","topic":"Linguistics and Cultural Studies","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Python (programming language); Natural language processing; Artificial intelligence; Vocabulary; Hidden Markov model; Parsing; Word (group theory); Programming language; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002013236,0.0001008393,0.0001207558,0.00001784539,0.002198715,0.003974954,0.0001089452,0.00002285592,0.0000468683],"category_scores_gemma":[0.00004728243,0.00005312155,0.00003533954,0.00002912668,0.00009495051,0.0009114556,0.00002998188,0.0001710028,0.00002888811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001496281,"about_ca_system_score_gemma":0.00002875886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002545233,"about_ca_topic_score_gemma":0.00001083683,"domain_scores_codex":[0.9991484,0.00001347974,0.0003919282,0.0000485027,0.0002457258,0.0001519185],"domain_scores_gemma":[0.9992853,0.00002903259,0.0002661771,0.00002880159,0.0002989096,0.00009173033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001110815,0.00001431851,0.0003147677,0.0006477696,0.0001429274,0.00001333034,0.7727667,0.0001572339,0.00002598956,0.04498892,0.05406216,0.1267548],"study_design_scores_gemma":[0.0002120707,0.00005092528,0.00006147039,0.0001095242,0.00001390725,0.0000307187,0.07278199,0.00561261,0.000002874648,0.00007873362,0.9209492,0.00009600865],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3972712,0.1230074,0.0101761,0.03933207,0.009802268,0.002222344,0.0002472103,0.0009456951,0.4169958],"genre_scores_gemma":[0.996624,0.0001083353,0.000009680653,0.0006081527,0.002276413,0.000005734199,0.000002896819,0.000004739847,0.0003600499],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.866887,"threshold_uncertainty_score":0.9991003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03106485387496861,"score_gpt":0.2177514394227578,"score_spread":0.1866865855477892,"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."}}