{"id":"W4311428537","doi":"10.3384/nejlt.2000-1533.2022.4315","title":"Part-of-Speech and Morphological Tagging of Algerian Judeo-Arabic","year":2022,"lang":"en","type":"article","venue":"Northern European Journal of Language Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; Natural language processing; Annotation; Arabic; Preprocessor; Pipeline (software); Artificial intelligence; Part of speech; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0006144456,0.0003889793,0.0002017307,0.002610513,0.001141506,0.0007654896,0.0004077101,0.0004935798,0.003358496],"category_scores_gemma":[0.002535133,0.0001923041,0.000189204,0.001704567,0.0005231891,0.0008272795,0.0005433368,0.0003595247,0.002231368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004512831,"about_ca_system_score_gemma":0.0005079855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004796105,"about_ca_topic_score_gemma":0.01017159,"domain_scores_codex":[0.9994821,0.0001517475,0.0000628284,0.0001666443,0.0001009864,0.0000357577],"domain_scores_gemma":[0.9972621,0.001201544,0.0002912763,0.0004148098,0.0007452202,0.00008502127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001192908,0.0003203502,0.05989053,0.001373649,0.00009209669,0.003761229,0.01422355,0.008956791,0.2957924,0.006235136,0.01867493,0.5894864],"study_design_scores_gemma":[0.00008433074,0.0002677372,0.3932351,0.0002942482,0.0001485801,0.00411036,0.01145755,0.1167407,0.2889008,0.005413044,0.1791356,0.0002119851],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.951947,0.0008960935,0.02673796,0.0003859096,0.0002186839,0.0001247229,0.006139412,0.001461422,0.01208894],"genre_scores_gemma":[0.9005495,0.0004868087,0.07479942,0.0001019851,0.0001027903,0.0001442358,0.01436596,0.0003593152,0.00909005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004796105,"threshold_uncertainty_score":0.01123524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0101339323969064,"score_gpt":0.2372624635259936,"score_spread":0.2271285311290872,"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."}}