{"id":"W1510117420","doi":"","title":"Extracting semantically-coherent keyphrases from speech","year":2004,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"University of Pennsylvania","keywords":"Computer science; Extractor; Artificial intelligence; Similarity (geometry); Word (group theory); Natural language processing; Speech recognition; Key (lock); Semantic similarity; Pattern recognition (psychology); Linguistics; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0001255537,0.000141319,0.0001876436,0.00007789559,0.00009386947,0.0001243495,0.0007689211,0.00005754297,0.0001557343],"category_scores_gemma":[0.000110997,0.0001299601,0.00009289178,0.0003014298,0.00003951303,0.0005192086,0.000247743,0.0001786221,0.0001676425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008156554,"about_ca_system_score_gemma":0.00004107804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006882366,"about_ca_topic_score_gemma":0.0000369095,"domain_scores_codex":[0.9986922,0.00002679898,0.0002381123,0.0004293631,0.0003352524,0.0002783469],"domain_scores_gemma":[0.9989557,0.0001276818,0.00009442067,0.000665748,0.00005976284,0.00009671146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000590529,0.000295648,0.001149488,0.000007910279,0.00006050727,0.0002629763,0.0004070405,0.0001609046,0.4661017,0.1612868,0.0005757984,0.3696854],"study_design_scores_gemma":[0.000234469,0.00003981027,0.001006508,0.00004979094,0.00001526028,0.00001261647,0.00002101691,0.002584573,0.3708709,0.6231477,0.001760447,0.0002568498],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09333073,0.00003607716,0.89324,0.001189089,0.00007425268,0.00008966419,0.000001289484,0.0006154084,0.0114235],"genre_scores_gemma":[0.5379673,0.000009577778,0.4617307,0.000168185,0.00005481417,0.000006461193,0.000001664028,0.000006687516,0.00005467819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.461861,"threshold_uncertainty_score":0.5299619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01515247210393721,"score_gpt":0.2731679085033432,"score_spread":0.2580154363994059,"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."}}