{"id":"W2605118633","doi":"10.1162/tacl_a_00047","title":"A Generative Model of Phonotactics","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Phonotactics; Computer science; Generative grammar; Artificial intelligence; Generative model; Feature (linguistics); Natural language processing; Set (abstract data type); Probabilistic logic; Phonology; Hierarchy; Linguistics; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000254952,0.0000710305,0.0001338327,0.00004740572,0.0004332192,0.00006782914,0.0008270067,0.00006379435,6.292266e-7],"category_scores_gemma":[0.001986112,0.00006065244,0.0001278084,0.0000730001,0.00004730103,0.0001021635,0.00003260541,0.00009714454,3.162312e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009731935,"about_ca_system_score_gemma":0.0001747023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001576382,"about_ca_topic_score_gemma":0.000006034748,"domain_scores_codex":[0.9992197,0.00002148004,0.0002578238,0.0001157711,0.0002954049,0.00008984499],"domain_scores_gemma":[0.9969627,0.0003097801,0.0008362265,0.0003366906,0.001536774,0.0000178018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001138807,0.0001052077,0.0003088743,0.0000471498,0.00009422466,5.817966e-8,0.0004823906,0.3868974,0.0006765085,0.6096516,0.0002542349,0.001470869],"study_design_scores_gemma":[0.0001710755,0.00001875547,0.0001462283,0.00001526745,0.00002930266,2.056099e-7,0.00000287609,0.6603733,0.01723513,0.3218551,0.00009820362,0.00005454304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002897388,0.00002950201,0.9979694,0.0005573906,0.0004200153,0.0001538915,0.0001167386,0.00004162658,0.0004216756],"genre_scores_gemma":[0.539434,0.000001335833,0.4602677,0.00002297327,0.00002828194,0.000005270612,0.000002096928,0.000003581399,0.0002348488],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5391442,"threshold_uncertainty_score":0.3332015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02717737201804962,"score_gpt":0.3050787880426549,"score_spread":0.2779014160246053,"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."}}