{"id":"W2964083623","doi":"10.3390/info10080246","title":"Text Filtering through Multi-Pattern Matching: A Case Study of Wu–Manber–Uy on the Language of Uyghur","year":2019,"lang":"en","type":"article","venue":"Information","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; York University","keywords":"Computer science; Spelling; Word (group theory); Word2vec; Artificial intelligence; Vowel; Natural language processing; Matching (statistics); Population; Field (mathematics); Linguistics; Speech recognition; Mathematics; Statistics; Sociology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002385951,0.00008858355,0.0001160296,0.00008176681,0.00004339263,0.00006850321,0.0004892821,0.00003573009,0.00001230543],"category_scores_gemma":[0.00003241278,0.00005861386,0.00002930069,0.0001846992,0.00001217298,0.001414972,0.0002007981,0.0001265873,0.00002816444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002106103,"about_ca_system_score_gemma":0.00001350148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00136873,"about_ca_topic_score_gemma":0.00004397865,"domain_scores_codex":[0.9992445,0.00003650558,0.0003014921,0.00008404513,0.0002342078,0.00009929386],"domain_scores_gemma":[0.9990798,0.00007670625,0.0002846426,0.000476665,0.00007062195,0.00001155055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002575099,0.0004081487,0.001466381,0.0005174062,0.00005604196,0.0001033206,0.7390774,0.0005501609,0.01047733,0.007135932,0.0002092822,0.2399728],"study_design_scores_gemma":[0.005316229,0.003125298,0.003790859,0.001560831,0.00006016519,0.001553478,0.1783903,0.2804075,0.5190629,0.004701165,0.0005131162,0.001518143],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8456202,0.00002610144,0.1534287,0.00006401186,0.00007075938,0.0003499409,0.000002753572,0.0001051182,0.0003324551],"genre_scores_gemma":[0.9747165,6.28057e-7,0.0250236,0.0002110402,0.000007486222,0.00001125524,0.000001947145,0.000003714463,0.00002381768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5606871,"threshold_uncertainty_score":0.2390204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01972880750755143,"score_gpt":0.2912128139284301,"score_spread":0.2714840064208787,"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."}}