{"id":"W2114705006","doi":"10.1016/j.csl.2009.02.004","title":"Syllabification rules versus data-driven methods in a language with low syllabic complexity: The case of Italian","year":2009,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University; National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Syllabification; Syllabic verse; Computer science; Syllable; Natural language processing; Artificial intelligence; Lexicon; Parsing; Machine translation; Speech recognition","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":[0.0007122052,0.0001797797,0.000306774,0.0001727183,0.00006745951,0.00004591591,0.0009433132,0.0001113524,0.0003511487],"category_scores_gemma":[0.0000322059,0.0001279124,0.00004134652,0.0004074013,0.0002453025,0.00006987,0.0002207048,0.0003663325,0.00007666605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003406567,"about_ca_system_score_gemma":0.00004175731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001569031,"about_ca_topic_score_gemma":0.001997575,"domain_scores_codex":[0.9981539,0.000579706,0.0002923248,0.0004641169,0.0001369702,0.0003729763],"domain_scores_gemma":[0.9977316,0.0003261399,0.0001245,0.001684714,0.00005721438,0.00007583893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007625508,0.0007642974,0.0005756235,0.00006018846,0.0002797251,0.01104375,0.06974898,0.00005360325,0.006581152,0.004493678,0.003859792,0.9017767],"study_design_scores_gemma":[0.0355254,0.009805937,0.6946598,0.000656809,0.0005789078,0.02006988,0.06976508,0.1315247,0.02069816,0.00539521,0.007219787,0.004100342],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873309,0.001038531,0.007143363,0.000847862,0.000371005,0.0004246289,0.0001127241,0.00005702838,0.002674005],"genre_scores_gemma":[0.9257321,0.00000724702,0.07345168,0.0002003632,0.0001847066,0.00001098991,0.0001967714,0.00002041998,0.0001957495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8976763,"threshold_uncertainty_score":0.5216116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08642458988048203,"score_gpt":0.441595487778507,"score_spread":0.355170897898025,"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."}}