{"id":"W2125247927","doi":"10.3115/1690219.1690223","title":"Summarizing multiple spoken documents","year":2009,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Salient; Transcription (linguistics); Speech recognition; Vocabulary; Word (group theory); Spoken language; Word error rate; Artificial intelligence; Natural language processing; Feature (linguistics); Language model; Independence (probability theory); Linguistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00009989908,0.0000580438,0.00006013912,0.00003710894,0.00004967533,0.0001034381,0.0004861486,0.00002281087,0.00002068842],"category_scores_gemma":[0.00001843819,0.00005066575,0.00002531741,0.00009469291,0.000003513063,0.0004039778,0.00009083965,0.00004993011,0.00009270485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001921148,"about_ca_system_score_gemma":0.00001245059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005033658,"about_ca_topic_score_gemma":0.000006484253,"domain_scores_codex":[0.999361,0.00001084345,0.0001065029,0.0002075022,0.000139168,0.0001749491],"domain_scores_gemma":[0.9995269,0.00002161503,0.00001914096,0.000363961,0.00001671918,0.00005167041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000269829,0.00006871339,0.008599536,0.000003346762,0.000008030412,0.00002500392,0.0005092249,0.0007217418,0.003868599,0.2800415,0.002527676,0.7036239],"study_design_scores_gemma":[0.0006726577,0.00006417915,0.01275792,0.00001690631,0.000002411395,0.00001182207,0.00001929278,0.926959,0.006121305,0.02818742,0.02486362,0.0003235024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02531146,0.0000243575,0.9295741,0.001371898,0.0001719154,0.00005885639,7.321015e-8,0.0002348636,0.04325246],"genre_scores_gemma":[0.7986836,0.000002088469,0.1985979,0.00101935,0.00003602068,8.208468e-7,2.874943e-7,0.000001459461,0.001658423],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9262372,"threshold_uncertainty_score":0.2066089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01945310161423677,"score_gpt":0.2523597196129386,"score_spread":0.2329066179987018,"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."}}