{"id":"W3139133216","doi":"10.1002/trc2.12147","title":"Multilingual automation of transcript preprocessing in Alzheimer's disease detection","year":2021,"lang":"en","type":"article","venue":"Alzheimer s & Dementia Translational Research & Clinical Interventions","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Preprocessor; Computer science; Pipeline (software); Natural language processing; Normalization (sociology); Scalability; Task (project management); Context (archaeology); Data pre-processing; Information extraction; Artificial intelligence; Machine learning; Programming language; Biology; Database","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":[0.00451807,0.001645457,0.0009877557,0.002550143,0.001201191,0.002304153,0.001116777,0.0007226497,0.02015957],"category_scores_gemma":[0.01414295,0.0006373063,0.001208661,0.001747791,0.0007081899,0.001879541,0.003607619,0.001350719,0.02326622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006223129,"about_ca_system_score_gemma":0.002854439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004118504,"about_ca_topic_score_gemma":0.00622205,"domain_scores_codex":[0.9957916,0.001843259,0.0003409777,0.001078457,0.0006728548,0.0002729034],"domain_scores_gemma":[0.991003,0.004066065,0.0005118496,0.001647849,0.002448366,0.0003228],"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":[0.00111626,0.0001444125,0.006709006,0.001638376,0.0001594631,0.0006387175,0.002059461,0.002355228,0.1396637,0.002302836,0.03183287,0.8113796],"study_design_scores_gemma":[0.0003595882,0.001111601,0.05992884,0.001086089,0.0006831442,0.004369784,0.004228183,0.1139861,0.4217898,0.03110962,0.3607359,0.0006113845],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04525796,0.001747202,0.8904732,0.0008360826,0.0004878136,0.0006831874,0.01007018,0.04270335,0.007741055],"genre_scores_gemma":[0.1674603,0.001054433,0.7957753,0.0003116623,0.0003417373,0.001041047,0.02283428,0.004414759,0.006766395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02015957,"threshold_uncertainty_score":0.06744051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3485853545168988,"score_gpt":0.4959002253631045,"score_spread":0.1473148708462058,"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."}}