{"id":"W3112745663","doi":"10.1002/alz.037526","title":"Multilingual text normalization for computer‐based detection of Alzheimer’s disease","year":2020,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Normalization (sociology); Computer science; Natural language processing; Pipeline (software); Artificial intelligence; Scalability; Task (project management); Context (archaeology); Correlation; Database; Programming language","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":[0.002415025,0.001368287,0.0008815638,0.00492703,0.0008334189,0.001601649,0.000970331,0.0006448793,0.006171594],"category_scores_gemma":[0.0112577,0.0003184965,0.0008338904,0.002440717,0.0005451306,0.001475899,0.001429717,0.0008400813,0.004974907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008609704,"about_ca_system_score_gemma":0.001209988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00281673,"about_ca_topic_score_gemma":0.003774539,"domain_scores_codex":[0.9966711,0.0008338962,0.0004559105,0.001129299,0.0007193331,0.0001905682],"domain_scores_gemma":[0.9915195,0.003498371,0.0008785183,0.00103768,0.002810036,0.0002558788],"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":[0.001280308,0.0003539502,0.01770387,0.001454132,0.0002643979,0.000606437,0.0008720097,0.003880429,0.1408778,0.001117918,0.0235965,0.8079923],"study_design_scores_gemma":[0.0001859006,0.001070721,0.1711331,0.0003981614,0.0006503381,0.002801592,0.002783301,0.2480498,0.4391018,0.006690881,0.1267554,0.0003790031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3821098,0.004713632,0.5196738,0.001323803,0.0009949434,0.001577588,0.02848293,0.05138452,0.009738958],"genre_scores_gemma":[0.4204421,0.0009535292,0.5238958,0.0002672923,0.0004318253,0.001699999,0.04434681,0.001522085,0.006440485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006171594,"threshold_uncertainty_score":0.02064598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03076037658845636,"score_gpt":0.2886944484029721,"score_spread":0.2579340718145158,"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."}}