{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004517332,0.0001599058,0.0001484299,0.0001496212,0.0002615238,0.0004465438,0.0005385982,0.0001272335,0.00004304894],"category_scores_gemma":[0.0003695731,0.0001490116,0.00007169243,0.0006000701,0.00007871354,0.0005178193,0.0001218258,0.0001554705,0.00001304946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001814674,"about_ca_system_score_gemma":0.0001599839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004281084,"about_ca_topic_score_gemma":0.0001040817,"domain_scores_codex":[0.9985685,0.00003138832,0.0002933458,0.000430788,0.0003778532,0.0002981004],"domain_scores_gemma":[0.9990214,0.0002163381,0.0001420982,0.000289792,0.0002716803,0.00005873666],"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":[0.0002025031,0.000295604,0.004729668,0.000335601,0.00006251846,0.001413666,0.002395772,0.0001066001,0.4852028,0.4175011,0.03656213,0.051192],"study_design_scores_gemma":[0.0007942785,0.000166787,0.0004724519,0.00004093131,0.000009412942,0.002002424,0.00004597703,0.07495128,0.7850811,0.1352613,0.0007046838,0.0004694077],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2373168,0.0003566385,0.7556276,0.0008075243,0.0003398188,0.0006254656,0.00000983385,0.001751845,0.003164462],"genre_scores_gemma":[0.3503046,4.477451e-7,0.6451628,0.0003155344,0.0001667446,0.000009513043,0.00002023213,0.00001119605,0.004009022],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2998782,"threshold_uncertainty_score":0.6076515,"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."}}