{"id":"W174563456","doi":"","title":"Evaluating automatic syllabification algorithms for English","year":2007,"lang":"en","type":"article","venue":"ePrints Soton (University of Southampton)","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Syllabification; Computer science; Syllable; Artificial intelligence; Natural language processing; Word (group theory); Task (project management); Set (abstract data type); Margin (machine learning); Speech recognition; Algorithm; Mathematics; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001738285,0.0001051704,0.0001993415,0.0001990619,0.0001970767,0.000008468096,0.0003851912,0.0001772116,0.003166096],"category_scores_gemma":[0.0001561594,0.0001352923,0.0001088547,0.0002212905,0.0001996664,0.00006043761,0.0001047303,0.0001870353,0.0003468484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005800875,"about_ca_system_score_gemma":0.00005081333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003323891,"about_ca_topic_score_gemma":0.0000545646,"domain_scores_codex":[0.9988082,0.00008103933,0.0001812411,0.0003450201,0.0002144693,0.0003699965],"domain_scores_gemma":[0.9986326,0.0003352987,0.0001696141,0.0004240433,0.0003291833,0.0001092852],"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":[0.0007914367,0.0008538177,0.02646163,0.0002121838,0.0005796739,0.000031518,0.2642588,0.0000335274,0.01918139,0.008189647,0.002281327,0.677125],"study_design_scores_gemma":[0.00546082,0.0006578983,0.9064256,0.00007356628,0.0001218053,0.00001067574,0.05838795,0.01234655,0.00302577,0.005335721,0.00759337,0.000560275],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9464908,0.00003313887,0.04447605,0.0001081647,0.000458413,0.0005310662,0.0000301368,0.00008069037,0.007791555],"genre_scores_gemma":[0.9819062,0.000003880754,0.01455034,0.00001766401,0.00007767443,0.000002402023,0.00002730315,0.00001444961,0.003400121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.879964,"threshold_uncertainty_score":0.9977452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1165340597800772,"score_gpt":0.3979764743016492,"score_spread":0.2814424145215719,"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."}}