{"id":"W1499800862","doi":"10.1007/3-540-45637-6_4","title":"Extracting Keyphrases from Spoken Audio Documents","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Utterance; Natural language processing; Speech recognition; Artificial intelligence; Robustness (evolution); Transcription (linguistics); Word error rate; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005904764,0.0007741007,0.0008245967,0.001104045,0.0003409041,0.0008677696,0.005330717,0.0003960829,0.0001708542],"category_scores_gemma":[0.0001774725,0.0007420782,0.0002549257,0.0008440294,0.0005532085,0.001814971,0.002158484,0.001142288,0.0001744206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005621972,"about_ca_system_score_gemma":0.0001975095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001070377,"about_ca_topic_score_gemma":0.00007952111,"domain_scores_codex":[0.9944054,0.00004512912,0.000791119,0.002390168,0.001500769,0.0008674287],"domain_scores_gemma":[0.9956086,0.0008728869,0.0006423391,0.002411152,0.0002334066,0.0002316168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000304556,0.00004482998,0.0001983128,0.00001228184,0.00003459001,0.0002813753,0.0004503982,0.005493646,0.0004207523,0.00591491,0.00009305069,0.9870528],"study_design_scores_gemma":[0.0003798421,0.0001690082,0.0002403011,0.0008949844,0.000044996,0.0000690742,2.527357e-7,0.3592879,0.01107111,0.6151019,0.0107735,0.001967168],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001128584,0.0008265157,0.9886834,0.0003683503,0.0008600013,0.0003253432,0.000007439263,0.0006059062,0.008210205],"genre_scores_gemma":[0.100125,0.0002190304,0.8964922,0.001150722,0.0006368253,0.00001439732,0.00001069433,0.00006038804,0.00129068],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9850857,"threshold_uncertainty_score":0.999503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01822006719168502,"score_gpt":0.2707262638742662,"score_spread":0.2525061966825812,"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."}}