{"id":"W2170774542","doi":"10.3115/1614049.1614065","title":"Investigating cross-language speech retrieval for a spontaneous conversational speech collection","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Clef; Natural language processing; Machine translation; Artificial intelligence; Speech recognition; Transcription (linguistics); Speech translation; Language model; Language translation; Speech corpus; Metadata; Task (project management); Information retrieval; Speech synthesis; World Wide Web; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01241698,0.001160987,0.001238757,0.002383272,0.001747132,0.002392969,0.00127787,0.001613028,0.0017538],"category_scores_gemma":[0.03526573,0.0004887161,0.001241245,0.00230515,0.001228272,0.003913241,0.002327029,0.001132669,0.001424845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053246,"about_ca_system_score_gemma":0.001126746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005161944,"about_ca_topic_score_gemma":0.006046679,"domain_scores_codex":[0.9873169,0.008037499,0.0009553349,0.001511371,0.001727962,0.0004509306],"domain_scores_gemma":[0.9548992,0.03299655,0.001540571,0.00411001,0.005787697,0.0006658959],"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":[0.0038524,0.006315534,0.04644087,0.006346332,0.001402829,0.00444355,0.02060067,0.05214639,0.3559641,0.006900083,0.01371014,0.4818771],"study_design_scores_gemma":[0.00140702,0.007545962,0.09274539,0.0001976339,0.0009261143,0.007210759,0.02119461,0.5397876,0.294091,0.008848859,0.02550189,0.0005431877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8913348,0.0009006162,0.1007928,0.0004093089,0.00009940656,0.0008087297,0.001405416,0.001914823,0.002334045],"genre_scores_gemma":[0.8773335,0.0004934927,0.1081078,0.0002528741,0.0002184031,0.001061767,0.009101784,0.0004113608,0.003019059],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01241698,"threshold_uncertainty_score":0.06566811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01176331994528935,"score_gpt":0.2831661493475073,"score_spread":0.2714028294022179,"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."}}