{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001030006,0.0004096071,0.0007000964,0.000999107,0.00121287,0.0009895698,0.0005499704,0.0008721565,0.001481972],"category_scores_gemma":[0.003780347,0.0001568837,0.0005166784,0.001664659,0.0008958414,0.002430201,0.001043776,0.000574904,0.0006333215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004565272,"about_ca_system_score_gemma":0.0007022339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01186669,"about_ca_topic_score_gemma":0.01353462,"domain_scores_codex":[0.9991904,0.000316703,0.00006779816,0.0001742683,0.0001749169,0.0000760083],"domain_scores_gemma":[0.9985878,0.0008129322,0.0001027641,0.0002230435,0.0002113083,0.00006223368],"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":[0.001235547,0.0007010256,0.03954877,0.00104482,0.0002429272,0.01633137,0.01632482,0.02452381,0.0850091,0.05785019,0.02605914,0.7311285],"study_design_scores_gemma":[0.0002457219,0.001073605,0.0413611,0.0001787409,0.0002244388,0.01045654,0.01167418,0.6178371,0.1030755,0.04301758,0.170595,0.0002605312],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8106694,0.001869372,0.1723218,0.001616969,0.0001261757,0.0003254398,0.0006175907,0.002983333,0.009469865],"genre_scores_gemma":[0.7455184,0.0005599078,0.2413029,0.0004888992,0.00009953234,0.0001319969,0.001065437,0.0004824653,0.01035044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01186669,"threshold_uncertainty_score":0.02359521,"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."}}