{"id":"W2169526216","doi":"10.1109/slt.2010.5700850","title":"An efficient approach for two-stage open vocabulary spoken term detection","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Vysoké Učení Technické v Brně; McGill University","keywords":"Search engine indexing; Computer science; Vocabulary; Term (time); Word (group theory); Speech recognition; Domain (mathematical analysis); Natural language processing; Artificial intelligence; Task (project management); Index (typography); Database index; Information retrieval; World Wide Web","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":[0.0009659198,0.0009971794,0.001476776,0.00317756,0.000812619,0.00208947,0.002045751,0.0008586105,0.007231719],"category_scores_gemma":[0.005016889,0.0004662441,0.0007711845,0.002490809,0.0004527732,0.002868828,0.002068949,0.001080172,0.007294577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000507966,"about_ca_system_score_gemma":0.001854647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002292712,"about_ca_topic_score_gemma":0.004324598,"domain_scores_codex":[0.9982186,0.0001909908,0.0001662746,0.0003343911,0.0009479882,0.0001418622],"domain_scores_gemma":[0.9969826,0.001019643,0.000166403,0.0006352991,0.001011318,0.0001846725],"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":[0.0004701234,0.000245838,0.001142574,0.0002173091,0.00005212349,0.0001112751,0.0002536974,0.002110839,0.1210536,0.004504795,0.003817368,0.8660206],"study_design_scores_gemma":[0.0003356322,0.00121085,0.006004685,0.00006045775,0.0001982865,0.002239727,0.0007663994,0.6286523,0.2920855,0.02495539,0.04318681,0.0003040837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01842389,0.000328989,0.9722812,0.00007659972,0.00008506614,0.000286215,0.0005590211,0.006291657,0.001667271],"genre_scores_gemma":[0.07952086,0.0001449667,0.9138716,0.00005487882,0.00007651951,0.000322426,0.002069063,0.0003050564,0.003634767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007231719,"threshold_uncertainty_score":0.02419251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0155403152632423,"score_gpt":0.3104132214472516,"score_spread":0.2948729061840093,"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."}}