{"id":"W2133932086","doi":"10.3115/1687878.1687897","title":"A ranking approach to stress prediction for letter-to-phoneme conversion","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stress (linguistics); Substring; Computer science; Speech recognition; Ranking (information retrieval); Pronunciation; Artificial intelligence; Word error rate; Support vector machine; Rank (graph theory); Sequence (biology); Speech synthesis; Natural language processing; Word (group theory); Pattern recognition (psychology); Mathematics","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":[0.000197685,0.0001005966,0.0001005402,0.0001482211,0.0001012837,0.0001541953,0.0006247839,0.00006058023,0.000002005316],"category_scores_gemma":[0.00003841884,0.00008421634,0.00003710092,0.0003387004,0.000005520788,0.0003616969,0.0001078756,0.00008076879,0.000007727347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004750743,"about_ca_system_score_gemma":0.00001411062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001240317,"about_ca_topic_score_gemma":7.285932e-7,"domain_scores_codex":[0.999081,0.00001551335,0.0001281469,0.0003592263,0.0001985652,0.000217592],"domain_scores_gemma":[0.999481,0.00002464235,0.00003182239,0.0002975901,0.00008083555,0.00008412869],"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":[0.0001476683,0.0004362381,0.0001803762,0.0001828721,0.0000232819,0.000009411603,0.005558494,0.0003735677,0.1415403,0.09587139,0.256835,0.4988414],"study_design_scores_gemma":[0.001267435,0.001154061,0.0005774088,0.0002514119,0.00001798828,0.00002466233,0.00007418577,0.205157,0.7450049,0.02337992,0.02221589,0.0008751559],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001420537,0.00005126049,0.9928126,0.003128431,0.0001379292,0.0005206348,0.000003474104,0.0009295319,0.0009955422],"genre_scores_gemma":[0.3190921,3.301183e-7,0.6747217,0.005856195,0.0001066778,0.00002446466,0.000004376489,0.000003879287,0.0001902824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6034646,"threshold_uncertainty_score":0.3434243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01320748164364175,"score_gpt":0.2530259903314433,"score_spread":0.2398185086878016,"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."}}