{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005994436,0.0001310554,0.0001245193,0.0000970069,0.0001878035,0.0006882182,0.002316101,0.00008804567,0.00001204605],"category_scores_gemma":[0.00003456757,0.0001025859,0.00004081841,0.0002213114,0.00003329087,0.0007000792,0.0004644115,0.0002230289,0.000003862392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002340688,"about_ca_system_score_gemma":0.00004371987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001199042,"about_ca_topic_score_gemma":0.00005145623,"domain_scores_codex":[0.998921,0.00002701258,0.0001501381,0.0004950237,0.0001624262,0.0002443434],"domain_scores_gemma":[0.998939,0.00002812153,0.00007246202,0.0007764866,0.00009126292,0.00009268644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003405925,0.0003199863,0.00008077061,0.00005054768,0.000009414928,0.000006910479,0.0004709408,0.0001292336,0.5650144,0.08157091,0.0001302047,0.3521826],"study_design_scores_gemma":[0.0002840821,0.0001063652,0.00006342399,0.000003661435,0.00000326505,0.00001926732,0.00001314203,0.4769448,0.5199277,0.002070752,0.0003629133,0.0002006092],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0294005,0.00003116004,0.9667857,0.00006662129,0.000197259,0.0007203304,0.000002174671,0.0008040675,0.001992157],"genre_scores_gemma":[0.4850569,7.406056e-8,0.5144114,0.0001389954,0.00004772673,0.00006585289,0.000004591101,0.000007861316,0.0002666183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4768156,"threshold_uncertainty_score":0.6636503,"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."}}