{"id":"W3041134523","doi":"10.1080/17517575.2020.1790043","title":"Valuing free-form text data from maintenance logs through transfer learning with CamemBERT","year":2020,"lang":"en","type":"article","venue":"Enterprise Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Exploit; Transfer of learning; Artificial intelligence; Machine learning; Scheduling (production processes); Engineering","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":[0.004921233,0.00114332,0.0006132933,0.002698372,0.0005113322,0.001871121,0.001851076,0.001748255,0.00327581],"category_scores_gemma":[0.01742328,0.0003981541,0.00109549,0.001580472,0.0005932,0.00351144,0.002262603,0.002320279,0.001932897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001691977,"about_ca_system_score_gemma":0.0008923167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006100094,"about_ca_topic_score_gemma":0.005533343,"domain_scores_codex":[0.9981666,0.0006723479,0.0001268584,0.0006287694,0.0002920698,0.0001133042],"domain_scores_gemma":[0.9947193,0.003438588,0.0002354802,0.0007269977,0.0007393897,0.000140238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001379071,0.001928561,0.01664226,0.0003913309,0.0003662521,0.000602763,0.001057528,0.1581736,0.01015954,0.004089648,0.01546434,0.7897452],"study_design_scores_gemma":[0.00005761404,0.0002302514,0.003644384,0.00003545313,0.00004088012,0.00005952897,0.0001710002,0.9812452,0.00513082,0.005122533,0.004218739,0.00004365882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4671751,0.001438841,0.4837464,0.001702446,0.0006733966,0.00113231,0.00370536,0.03037917,0.01004704],"genre_scores_gemma":[0.8353755,0.0002394079,0.1516253,0.0002984146,0.0001050425,0.0005681018,0.006110881,0.0003560027,0.00532134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006100094,"threshold_uncertainty_score":0.02602625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03381081355604557,"score_gpt":0.2467317373066045,"score_spread":0.212920923750559,"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."}}