{"id":"W2160547679","doi":"10.3115/1687878.1687898","title":"Reducing the annotation effort for letter-to-phoneme conversion","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Classifier (UML); Natural language processing; Artificial intelligence; Cluster analysis; Speech recognition; Training set; Machine learning","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":[0.001715826,0.001480042,0.001369443,0.001410327,0.00131714,0.001860558,0.002408596,0.001264,0.01004708],"category_scores_gemma":[0.01272453,0.0006203981,0.0007329097,0.00169069,0.0006796838,0.003083465,0.002345244,0.00182374,0.01272576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006299189,"about_ca_system_score_gemma":0.001857244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006012076,"about_ca_topic_score_gemma":0.01205959,"domain_scores_codex":[0.9971306,0.001086224,0.0001588102,0.0006251691,0.0008264338,0.0001728083],"domain_scores_gemma":[0.9882604,0.005461008,0.0004797273,0.003013,0.00256461,0.0002212698],"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":[0.0005740168,0.0003048406,0.003222099,0.0002947347,0.00004176465,0.0002022346,0.0006950679,0.007120775,0.08115881,0.001884564,0.01197482,0.8925263],"study_design_scores_gemma":[0.00020718,0.0006620182,0.01739368,0.0001748632,0.0002696007,0.001758962,0.002162522,0.4144313,0.4296366,0.01814413,0.1149307,0.0002283601],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1537934,0.001159057,0.8013087,0.001137181,0.0003574265,0.0003501691,0.001403009,0.0294905,0.01100054],"genre_scores_gemma":[0.3172413,0.0005667019,0.6572782,0.0005111253,0.0001664376,0.0004228178,0.005346848,0.002522166,0.01594444],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01004708,"threshold_uncertainty_score":0.03361082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01142126957735392,"score_gpt":0.2732580540577467,"score_spread":0.2618367844803928,"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."}}