{"id":"W2783291346","doi":"10.63317/3e7ocg3pz9e6","title":"Manual vs Automatic Bitext Extraction","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Extraction (chemistry); Speech recognition; Natural language processing; Pattern recognition (psychology); Chromatography","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":[0.003959907,0.0009575466,0.001006078,0.002865042,0.0008177364,0.003374737,0.001311921,0.00166925,0.02311588],"category_scores_gemma":[0.01512358,0.0004860174,0.001003592,0.00195152,0.0005069845,0.003722756,0.001884386,0.001495262,0.00945732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000325663,"about_ca_system_score_gemma":0.0008754219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001229233,"about_ca_topic_score_gemma":0.002097658,"domain_scores_codex":[0.9956891,0.001656478,0.0005248373,0.0006309696,0.001066013,0.0004325682],"domain_scores_gemma":[0.989843,0.006753612,0.0003431287,0.001836373,0.00107523,0.0001487946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005040477,0.0006339155,0.007810285,0.001403786,0.0003176157,0.0005350616,0.0002457,0.004427084,0.05217815,0.00797875,0.04328682,0.8761423],"study_design_scores_gemma":[0.001789045,0.00329166,0.09179099,0.001233315,0.002206217,0.006929694,0.002312022,0.3052323,0.3836231,0.04626388,0.1548959,0.0004317789],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5407723,0.008958031,0.2891567,0.003037155,0.003825229,0.00133289,0.03117313,0.03265823,0.08908635],"genre_scores_gemma":[0.7379522,0.002580616,0.1815662,0.0008297354,0.0007212593,0.0003985182,0.03651526,0.002831857,0.0366043],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02311588,"threshold_uncertainty_score":0.07733029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01129067223717467,"score_gpt":0.3104030726975384,"score_spread":0.2991124004603637,"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."}}