{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005774554,0.0005940939,0.000464594,0.0008644345,0.0008166011,0.001171637,0.00083287,0.0003744721,0.01226161],"category_scores_gemma":[0.001820928,0.0003560087,0.0004835305,0.0006246084,0.0003346599,0.001853658,0.001088169,0.0009787364,0.007264995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005146224,"about_ca_system_score_gemma":0.002002454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00713016,"about_ca_topic_score_gemma":0.007387466,"domain_scores_codex":[0.9995765,0.00006940178,0.00003641924,0.0001537979,0.0001060523,0.00005777495],"domain_scores_gemma":[0.9994988,0.0001253207,0.00004436103,0.00007188333,0.0002303217,0.00002930047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001266803,0.0002744006,0.02937835,0.001086999,0.0001247485,0.001266301,0.001606324,0.007248026,0.05196967,0.01251048,0.0758783,0.8173896],"study_design_scores_gemma":[0.0001782699,0.001023741,0.06289952,0.0005505261,0.0003276315,0.004359851,0.00282347,0.2164369,0.2671165,0.02136036,0.4225354,0.0003878407],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3949938,0.003500194,0.4276432,0.002169929,0.0009502451,0.0008875479,0.0549942,0.06681944,0.04804149],"genre_scores_gemma":[0.6434845,0.001254158,0.2687346,0.0002978403,0.00009640803,0.0005711658,0.0519544,0.00197107,0.03163586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01226161,"threshold_uncertainty_score":0.04101914,"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."}}