{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003701972,0.0001607783,0.0002980726,0.0004716532,0.0002332895,0.0001655539,0.0005460578,0.0001332405,0.0007293851],"category_scores_gemma":[0.0009753298,0.0001759715,0.000696241,0.001183313,0.0002360363,0.0008818306,0.00009817583,0.0005233268,0.00007454051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001347861,"about_ca_system_score_gemma":0.0004055735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004698946,"about_ca_topic_score_gemma":0.0005625135,"domain_scores_codex":[0.9949125,0.001352225,0.001573813,0.0007208525,0.001039786,0.0004008166],"domain_scores_gemma":[0.9967436,0.001312345,0.0001831119,0.00049413,0.001005979,0.0002608025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00008876327,0.002077218,0.006987697,0.00005618907,0.001688476,0.00004276551,0.0002973542,0.0001063998,0.001484169,0.003416187,0.00006972581,0.9836851],"study_design_scores_gemma":[0.004582898,0.0004147392,0.5449957,0.001696929,0.002745404,0.00002414958,0.0003826241,0.2535028,0.1334085,0.05428462,0.003091309,0.0008703987],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1501665,0.05487495,0.7833081,0.006149623,0.001246402,0.001308736,0.0001010007,0.0002684791,0.002576175],"genre_scores_gemma":[0.9690371,0.0001417532,0.03050743,0.00005831379,0.00006798637,0.00009774279,0.00005477951,0.00001469519,0.00002023533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9828147,"threshold_uncertainty_score":0.7986255,"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."}}