{"id":"W2909676388","doi":"10.1017/s0952675720000056","title":"An algorithm for learning phonological classes from distributional similarity","year":2020,"lang":"en","type":"article","venue":"Phonology","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Phonology; Phonological rule; Computer science; Similarity (geometry); Set (abstract data type); Natural (archaeology); Artificial intelligence; Natural language processing; Natural language; Speech recognition; Linguistics; Image (mathematics)","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":[0.00157633,0.00100313,0.001118257,0.002298581,0.001081067,0.001721677,0.002935739,0.002211062,0.007476259],"category_scores_gemma":[0.006679822,0.000711997,0.001348439,0.001633008,0.0009349781,0.002912912,0.002046816,0.002344304,0.002812686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001148221,"about_ca_system_score_gemma":0.001730113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004420852,"about_ca_topic_score_gemma":0.006134963,"domain_scores_codex":[0.9988758,0.0001720868,0.0001141945,0.0004943301,0.0002481285,0.00009537329],"domain_scores_gemma":[0.9979324,0.001219014,0.00009087689,0.0002335206,0.0004485961,0.00007555386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001773511,0.0001587783,0.001656068,0.00009774642,0.00007552063,0.00005919829,0.0001598701,0.02715769,0.004997496,0.008334599,0.005199265,0.9519265],"study_design_scores_gemma":[0.0001617884,0.0001257152,0.000867651,0.00003775552,0.00005102357,0.000211907,0.0001463105,0.931722,0.006425739,0.05419207,0.006026061,0.00003200522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01051348,0.0001130677,0.9840255,0.0001678827,0.00004484043,0.000175943,0.0001859112,0.003295192,0.001478073],"genre_scores_gemma":[0.0954148,0.00008299484,0.8994645,0.0001924784,0.00005530236,0.0004221377,0.001108378,0.000300446,0.002958974],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007476259,"threshold_uncertainty_score":0.02501059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08843556346368177,"score_gpt":0.3850009426556763,"score_spread":0.2965653791919945,"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."}}